{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/speech-emotion-recognition","name":"Speech Emotion Recognition","slug":"speech-emotion-recognition","description_markdown":"**Speech Emotion Recognition** is a task of speech processing and computational paralinguistics that aims to recognize and categorize the emotions expressed in spoken language. The goal is to determine the emotional state of a speaker, such as happiness, anger, sadness, or frustration, from their speech patterns, such as prosody, pitch, and rhythm.\r\n\r\nFor multimodal emotion recognition, please upload your result to [Multimodal Emotion Recognition on IEMOCAP](https://paperswithcode.com/sota/multimodal-emotion-recognition-on-iemocap)","categories":[{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":431,"papers_with_code":139,"benchmarks":16,"benchmark_tables_in_archive":16,"benchmark_tables_shown":16,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":22,"subtasks":4,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/speech-emotion-recognition-on-crema-d","slug":"speech-emotion-recognition-on-crema-d","dataset":"CREMA-D","dataset_url":"/dataset/crema-d","rows_in_archive":9,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Vertically long patch ViT","paper_title":"Accuracy enhancement method for speech emotion recognition from spectrogram using temporal frequency correlation and positional information learning through knowledge transfer","paper_url":"/paper/accuracy-enhancement-method-for-speech","paper_date":"2024-03-26","arxiv_id":"2403.17327","code_links":[{"title":"kjy7567/speech_emotion_recognition_from_log_Mel_spectrogram_using_vertically_long_patch","url":"https://github.com/kjy7567/speech_emotion_recognition_from_log_Mel_spectrogram_using_vertically_long_patch"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-iemocap","slug":"speech-emotion-recognition-on-iemocap","dataset":"IEMOCAP","dataset_url":"/dataset/iemocap","rows_in_archive":8,"metrics":["UA CV","WA CV","UA","WA","F1"],"first_row_in_archive_order":{"model":"SER with MTL","paper_title":"Speech Emotion Recognition with Multi-Task Learning","paper_url":"/paper/speech-emotion-recognition-with-multi-task","paper_date":"2021-09-06","arxiv_id":null,"code_links":[{"title":"TideDancer/interspeech21_emotion","url":"https://github.com/TideDancer/interspeech21_emotion"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-ravdess","slug":"speech-emotion-recognition-on-ravdess","dataset":"RAVDESS","dataset_url":"/dataset/ravdess","rows_in_archive":5,"metrics":["Accuracy","F1 Score","Precision","Recall","F1"],"first_row_in_archive_order":{"model":"VQ-MAE-S-12 (Frame) + Query2Emo","paper_title":"A vector quantized masked autoencoder for speech emotion recognition","paper_url":"/paper/a-vector-quantized-masked-autoencoder-for","paper_date":"2023-04-21","arxiv_id":"2304.11117","code_links":[{"title":"samsad35/VQ-MAE-S-code","url":"https://github.com/samsad35/VQ-MAE-S-code"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-msp-podcast","slug":"speech-emotion-recognition-on-msp-podcast","dataset":"MSP-Podcast (Valence)","dataset_url":"/dataset/msp-podcast","rows_in_archive":4,"metrics":["CCC"],"first_row_in_archive_order":{"model":"wav2small-Teacher","paper_title":"Wav2Small: Distilling Wav2Vec2 to 72K parameters for Low-Resource Speech emotion recognition","paper_url":"/paper/wav2small-distilling-wav2vec2-to-72k-1","paper_date":"2024-08-25","arxiv_id":"2408.13920","code_links":[{"title":"dkounadis/wav2small","url":"https://github.com/dkounadis/wav2small"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-msp-podcast-1","slug":"speech-emotion-recognition-on-msp-podcast-1","dataset":"MSP-Podcast (Activation)","dataset_url":"/dataset/msp-podcast","rows_in_archive":4,"metrics":["CCC"],"first_row_in_archive_order":{"model":"wav2small-Teacher","paper_title":"Wav2Small: Distilling Wav2Vec2 to 72K parameters for Low-Resource Speech emotion recognition","paper_url":"/paper/wav2small-distilling-wav2vec2-to-72k-1","paper_date":"2024-08-25","arxiv_id":"2408.13920","code_links":[{"title":"dkounadis/wav2small","url":"https://github.com/dkounadis/wav2small"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-msp-podcast-2","slug":"speech-emotion-recognition-on-msp-podcast-2","dataset":"MSP-Podcast (Dominance)","dataset_url":"/dataset/msp-podcast","rows_in_archive":4,"metrics":["CCC"],"first_row_in_archive_order":{"model":"wav2small-Teacher","paper_title":"Wav2Small: Distilling Wav2Vec2 to 72K parameters for Low-Resource Speech emotion recognition","paper_url":"/paper/wav2small-distilling-wav2vec2-to-72k-1","paper_date":"2024-08-25","arxiv_id":"2408.13920","code_links":[{"title":"dkounadis/wav2small","url":"https://github.com/dkounadis/wav2small"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-berst","slug":"speech-emotion-recognition-on-berst","dataset":"BERSt","dataset_url":"/dataset/berst","rows_in_archive":3,"metrics":["Unweighted Accuracy (UA)","Weighted Accuracy (WA)"],"first_row_in_archive_order":{"model":"DAWN-hidden-SVM","paper_title":"BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition","paper_url":"/paper/bersting-at-the-screams-a-benchmark-for","paper_date":"2025-04-30","arxiv_id":"2505.00059","code_links":[{"title":"myHaiven/data-collection","url":"https://github.com/myHaiven/data-collection"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-resd","slug":"speech-emotion-recognition-on-resd","dataset":"RESD","dataset_url":"/dataset/resd","rows_in_archive":3,"metrics":["Weighted Accuracy (WA)","Unweighted Accuracy (UA)","Weighted F1"],"first_row_in_archive_order":{"model":"emotion2vec+base","paper_title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","paper_url":"/paper/emotion2vec-self-supervised-pre-training-for","paper_date":"2023-12-23","arxiv_id":"2312.15185","code_links":[{"title":"alibaba-damo-academy/FunASR","url":"https://github.com/alibaba-damo-academy/FunASR"},{"title":"ddlBoJack/emotion2vec","url":"https://github.com/ddlBoJack/emotion2vec"}],"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":8,"n_pointer_only":9,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/emotion2vec-self-supervised-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2312.15185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15185"}},"official":{"repos":["ddlBoJack/emotion2vec"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}}},{"leaderboard":"/sota/speech-emotion-recognition-on-dusha-crowd","slug":"speech-emotion-recognition-on-dusha-crowd","dataset":"Dusha Crowd","dataset_url":"/dataset/dusha","rows_in_archive":1,"metrics":["Macro F1","UA","WA"],"first_row_in_archive_order":{"model":"Dusha baseline","paper_title":"Large Raw Emotional Dataset with Aggregation Mechanism","paper_url":"/paper/large-raw-emotional-dataset-with-aggregation","paper_date":"2022-12-23","arxiv_id":"2212.12266","code_links":[{"title":"salute-developers/golos","url":"https://github.com/salute-developers/golos"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-raw-emotional-dataset-with-aggregation#ran","syntology_url":"https://syntology.ai/paper/2212.12266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.12266"}},"official":{"repos":["salute-developers/golos"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}}},{"leaderboard":"/sota/speech-emotion-recognition-on-dusha-podcast","slug":"speech-emotion-recognition-on-dusha-podcast","dataset":"Dusha Podcast","dataset_url":"/dataset/dusha","rows_in_archive":1,"metrics":["Macro F1","UA","WA"],"first_row_in_archive_order":{"model":"Dusha baseline","paper_title":"Large Raw Emotional Dataset with Aggregation Mechanism","paper_url":"/paper/large-raw-emotional-dataset-with-aggregation","paper_date":"2022-12-23","arxiv_id":"2212.12266","code_links":[{"title":"salute-developers/golos","url":"https://github.com/salute-developers/golos"}],"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-raw-emotional-dataset-with-aggregation#ran","syntology_url":"https://syntology.ai/paper/2212.12266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.12266"}},"official":{"repos":["salute-developers/golos"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}}},{"leaderboard":"/sota/speech-emotion-recognition-on-emodb-1","slug":"speech-emotion-recognition-on-emodb-1","dataset":"EMODB","dataset_url":null,"rows_in_archive":1,"metrics":["1:1 Accuracy"],"first_row_in_archive_order":{"model":"VGG-optiVMD","paper_title":"An Extended Variational Mode Decomposition Algorithm Developed Speech Emotion Recognition Performance","paper_url":"/paper/an-extended-variational-mode-decomposition-1","paper_date":"2023-12-18","arxiv_id":"2312.10937","code_links":[{"title":"DavidHason/VGG-optiVMD","url":"https://github.com/DavidHason/VGG-optiVMD"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-emodb-dataset","slug":"speech-emotion-recognition-on-emodb-dataset","dataset":"EmoDB Dataset","dataset_url":"/dataset/emodb-dataset","rows_in_archive":1,"metrics":["Accuracy","F1"],"first_row_in_archive_order":{"model":"VQ-MAE-S-12 (Frame) + Query2Emo","paper_title":"A vector quantized masked autoencoder for speech emotion recognition","paper_url":"/paper/a-vector-quantized-masked-autoencoder-for","paper_date":"2023-04-21","arxiv_id":"2304.11117","code_links":[{"title":"samsad35/VQ-MAE-S-code","url":"https://github.com/samsad35/VQ-MAE-S-code"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-lssed","slug":"speech-emotion-recognition-on-lssed","dataset":"LSSED","dataset_url":"/dataset/lssed","rows_in_archive":1,"metrics":["Unweighted Accuracy (UA)"],"first_row_in_archive_order":{"model":"PyResNet","paper_title":"LSSED: a large-scale dataset and benchmark for speech emotion recognition","paper_url":"/paper/lssed-a-large-scale-dataset-and-benchmark-for","paper_date":"2021-01-30","arxiv_id":"2102.01754","code_links":[{"title":"tobefans/LSSED","url":"https://github.com/tobefans/LSSED"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-msp-improv","slug":"speech-emotion-recognition-on-msp-improv","dataset":"MSP-IMPROV","dataset_url":"/dataset/msp-improv","rows_in_archive":1,"metrics":["UA"],"first_row_in_archive_order":{"model":"emoDARTS","paper_title":"emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition","paper_url":"/paper/emodarts-joint-optimisation-of-cnn-sequential","paper_date":"2024-03-21","arxiv_id":"2403.14083","code_links":[{"title":"jayaneetha/emoDARTS","url":"https://github.com/jayaneetha/emoDARTS"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-quechua-ser","slug":"speech-emotion-recognition-on-quechua-ser","dataset":"Quechua-SER","dataset_url":"/dataset/quechua-ser","rows_in_archive":1,"metrics":["CCC (Arousal)","CCC (Valence)"],"first_row_in_archive_order":{"model":"LSTM","paper_title":"A speech corpus of Quechua Collao for automatic dimensional emotion recognition","paper_url":"/paper/a-speech-corpus-of-quechua-collao-for","paper_date":"2022-12-24","arxiv_id":null,"code_links":[{"title":"qccData/qccCorpus","url":"https://github.com/qccData/qccCorpus"}],"syntology":null}},{"leaderboard":"/sota/speech-emotion-recognition-on-shemo","slug":"speech-emotion-recognition-on-shemo","dataset":"ShEMO","dataset_url":"/dataset/shemo","rows_in_archive":1,"metrics":["Unweighted Accuracy"],"first_row_in_archive_order":{"model":"CNN (1D)","paper_title":"Emotion Recognition In Persian Speech Using Deep Neural Networks","paper_url":"/paper/emotion-recognition-in-persian-speech-using","paper_date":"2022-04-28","arxiv_id":"2204.13601","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/iemocap","name":"IEMOCAP","full_name":"The Interactive Emotional Dyadic Motion Capture (IEMOCAP) Database","num_papers_in_archive":749},{"url":"/dataset/meld","name":"MELD","full_name":"Multimodal EmotionLines Dataset","num_papers_in_archive":289},{"url":"/dataset/msp-improv","name":"MSP-IMPROV","full_name":"MSP-IMPROV: An Acted Corpus of Dyadic Interactions to Study Emotion Perception","num_papers_in_archive":70},{"url":"/dataset/crema-d","name":"CREMA-D","full_name":"CREMA-D","num_papers_in_archive":28},{"url":"/dataset/ravdess","name":"RAVDESS","full_name":"Ryerson Audio-Visual Database of Emotional Speech and Song","num_papers_in_archive":27},{"url":"/dataset/shemo","name":"ShEMO","full_name":"Sharif Emotional Speech Database","num_papers_in_archive":16},{"url":"/dataset/msp-podcast","name":"MSP-Podcast","full_name":"A large naturalistic speech emotional dataset","num_papers_in_archive":9},{"url":"/dataset/emodb-dataset","name":"EmoDB Dataset","full_name":"Berlin Database of Emotional Speech","num_papers_in_archive":6},{"url":"/dataset/lssed","name":"LSSED","full_name":"","num_papers_in_archive":6},{"url":"/dataset/resd","name":"RESD","full_name":"Russian Emotional Speech Dialogs with annotated text","num_papers_in_archive":3},{"url":"/dataset/sewa-db","name":"SEWA DB","full_name":"","num_papers_in_archive":3},{"url":"/dataset/dusha","name":"Dusha","full_name":"Dusha Crowd, Dusha Podcast","num_papers_in_archive":2},{"url":"/dataset/nemo-1","name":"nEMO","full_name":"","num_papers_in_archive":2},{"url":"/dataset/aesi","name":"AESI","full_name":"Athens Emotional States Inventory","num_papers_in_archive":1},{"url":"/dataset/berst","name":"BERSt","full_name":"Basic Emotion Random phrase Shouts","num_papers_in_archive":1},{"url":"/dataset/emofilm","name":"EmoFilm","full_name":"Emotional speech from Films","num_papers_in_archive":1},{"url":"/dataset/modified-shemo","name":"modified_shemo","full_name":"","num_papers_in_archive":1},{"url":"/dataset/quechua-ser","name":"Quechua-SER","full_name":"","num_papers_in_archive":1},{"url":"/dataset/ses","name":"SES","full_name":"Spanish Emotional Speech","num_papers_in_archive":1},{"url":"/dataset/vnemos","name":"VNEMOS","full_name":"Vietnamese Speech Emotion Dataset","num_papers_in_archive":1},{"url":"/dataset/jtes","name":"JTES","full_name":"Japanese Twitter-based Emotional Speech","num_papers_in_archive":0}],"subtasks":[{"url":"/task/culture","name":"Cultural Vocal Bursts Intensity Prediction"},{"url":"/task/high","name":"Vocal Bursts Intensity Prediction"},{"url":"/task/two","name":"Vocal Bursts Valence Prediction"},{"url":"/task/type","name":"Vocal Bursts Type Prediction"}],"parent_tasks":[{"url":"/task/emotion-recognition","name":"Emotion Recognition"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":5,"rows_per_page":100,"shown":100,"of":431,"of_with_code":139,"tagged_in_all":431,"counts":{"archive_papers_tagged":431,"with_a_code_link":139,"where_syntology_ran_a_sample":15,"not_listed_spam_title":0,"listed":431,"listed_where_code_ran":15,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":13,"every_run_a_failure_of_syntologys_instrument":2,"listed_with_a_run_with_no_instrument_failure":13,"listed_every_run_a_failure_of_syntologys_instrument":2,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/attention-is-all-you-need","slug":"attention-is-all-you-need","title":"Attention Is All You Need","date":"2017-06-12","arxiv_id":"1706.03762","repositories_listed":595,"syntology":{"n":946,"n_ran":610,"n_constructed":293,"n_ran_checked":529,"n_instrument":81,"n_unverified":336,"n_honours":45,"n_violates":15,"n_no_contract":469,"n_pointer_only":451,"phrase":"610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified","sample_list":"/paper/attention-is-all-you-need#ran","syntology_url":"https://syntology.ai/paper/1706.03762","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1706.03762"}},"official":{"repos":["tensorflow/tensor2tensor"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}},{"url":"/paper/continuous-control-with-deep-reinforcement","slug":"continuous-control-with-deep-reinforcement","title":"Continuous control with deep reinforcement learning","date":"2015-09-09","arxiv_id":"1509.02971","repositories_listed":161,"syntology":{"n":306,"n_ran":163,"n_constructed":126,"n_ran_checked":152,"n_instrument":11,"n_unverified":143,"n_honours":3,"n_violates":0,"n_no_contract":149,"n_pointer_only":163,"phrase":"163 ran (of which 126 constructed an object rather than computing a result; 152 with no instrument failure: 3 honoured, 0 violated, 149 with no contract checked; 11 where Syntology's instrument failed) · 143 unverified","sample_list":"/paper/continuous-control-with-deep-reinforcement#ran","syntology_url":"https://syntology.ai/paper/1509.02971","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.02971"}},"official":null}},{"url":"/paper/ast-audio-spectrogram-transformer","slug":"ast-audio-spectrogram-transformer","title":"AST: Audio Spectrogram Transformer","date":"2021-04-05","arxiv_id":"2104.01778","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/ast-audio-spectrogram-transformer#ran","syntology_url":"https://syntology.ai/paper/2104.01778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.01778"}},"official":{"repos":["YuanGongND/ast"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/multimodal-speech-emotion-recognition-and","slug":"multimodal-speech-emotion-recognition-and","title":"Multimodal Speech Emotion Recognition and Ambiguity Resolution","date":"2019-04-12","arxiv_id":"1904.06022","repositories_listed":5,"syntology":null},{"url":"/paper/multimodal-speech-emotion-recognition-using","slug":"multimodal-speech-emotion-recognition-using","title":"Multimodal Speech Emotion Recognition Using Audio and Text","date":"2018-10-10","arxiv_id":"1810.04635","repositories_listed":4,"syntology":null},{"url":"/paper/speech-emotion-diarization-which-emotion","slug":"speech-emotion-diarization-which-emotion","title":"Speech Emotion Diarization: Which Emotion Appears When?","date":"2023-06-22","arxiv_id":"2306.12991","repositories_listed":3,"syntology":null},{"url":"/paper/compact-graph-architecture-for-speech-emotion","slug":"compact-graph-architecture-for-speech-emotion","title":"Compact Graph Architecture for Speech Emotion Recognition","date":"2020-08-05","arxiv_id":"2008.02063","repositories_listed":3,"syntology":null},{"url":"/paper/cosyvoice-3-towards-in-the-wild-speech","slug":"cosyvoice-3-towards-in-the-wild-speech","title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","date":"2025-05-23","arxiv_id":"2505.17589","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/cosyvoice-3-towards-in-the-wild-speech#ran","syntology_url":"https://syntology.ai/paper/2505.17589","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17589"}},"official":{"repos":["funaudiollm/cosyvoice"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/unveiling-hidden-factors-explainable-ai-for","slug":"unveiling-hidden-factors-explainable-ai-for","title":"Unveiling Hidden Factors: Explainable AI for Feature Boosting in Speech Emotion Recognition","date":"2024-06-01","arxiv_id":"2406.01624","repositories_listed":2,"syntology":null},{"url":"/paper/emotion2vec-self-supervised-pre-training-for","slug":"emotion2vec-self-supervised-pre-training-for","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","date":"2023-12-23","arxiv_id":"2312.15185","repositories_listed":2,"syntology":{"n":20,"n_ran":17,"n_constructed":0,"n_ran_checked":11,"n_instrument":6,"n_unverified":3,"n_honours":1,"n_violates":2,"n_no_contract":8,"n_pointer_only":9,"phrase":"17 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 2 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 3 unverified","sample_list":"/paper/emotion2vec-self-supervised-pre-training-for#ran","syntology_url":"https://syntology.ai/paper/2312.15185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2312.15185"}},"official":{"repos":["ddlBoJack/emotion2vec"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/lauragpt-listen-attend-understand-and","slug":"lauragpt-listen-attend-understand-and","title":"LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT","date":"2023-10-07","arxiv_id":"2310.04673","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lauragpt-listen-attend-understand-and#ran","syntology_url":"https://syntology.ai/paper/2310.04673","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.04673"}},"official":null}},{"url":"/paper/a-persian-asr-based-ser-modification-of","slug":"a-persian-asr-based-ser-modification-of","title":"A Persian ASR-based SER: Modification of Sharif Emotional Speech Database and Investigation of Persian Text Corpora","date":"2022-11-18","arxiv_id":"2211.09956","repositories_listed":2,"syntology":null},{"url":"/paper/serab-a-multi-lingual-benchmark-for-speech","slug":"serab-a-multi-lingual-benchmark-for-speech","title":"SERAB: A multi-lingual benchmark for speech emotion recognition","date":"2021-10-07","arxiv_id":"2110.03414","repositories_listed":2,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":5,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":1,"n_no_contract":3,"n_pointer_only":2,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/serab-a-multi-lingual-benchmark-for-speech#ran","syntology_url":"https://syntology.ai/paper/2110.03414","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.03414"}},"official":{"repos":["neclow/serab"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/emotion-recognition-from-speech-using-wav2vec","slug":"emotion-recognition-from-speech-using-wav2vec","title":"Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings","date":"2021-04-08","arxiv_id":"2104.03502","repositories_listed":2,"syntology":null},{"url":"/paper/seen-and-unseen-emotional-style-transfer-for","slug":"seen-and-unseen-emotional-style-transfer-for","title":"Seen and Unseen emotional style transfer for voice conversion with a new emotional speech dataset","date":"2020-10-28","arxiv_id":"2010.14794","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-based-emotion-recognition","slug":"deep-learning-based-emotion-recognition","title":"Deep Learning based Emotion Recognition System Using Speech Features and Transcriptions","date":"2019-06-11","arxiv_id":"1906.05681","repositories_listed":2,"syntology":null},{"url":"/paper/190410788","slug":"190410788","title":"Speech Emotion Recognition Using Multi-hop Attention Mechanism","date":"2019-04-23","arxiv_id":"1904.10788","repositories_listed":2,"syntology":null},{"url":"/paper/dynamic-parameter-memory-temporary-lora","slug":"dynamic-parameter-memory-temporary-lora","title":"Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation","date":"2025-07-11","arxiv_id":"2507.09076","repositories_listed":1,"syntology":null},{"url":"/paper/medusa-a-multimodal-deep-fusion-multi-stage","slug":"medusa-a-multimodal-deep-fusion-multi-stage","title":"MEDUSA: A Multimodal Deep Fusion Multi-Stage Training Framework for Speech Emotion Recognition in Naturalistic Conditions","date":"2025-06-11","arxiv_id":"2506.09556","repositories_listed":1,"syntology":null},{"url":"/paper/2506-08717","slug":"2506-08717","title":"Multi-Teacher Language-Aware Knowledge Distillation for Multilingual Speech Emotion Recognition","date":"2025-06-10","arxiv_id":"2506.08717","repositories_listed":1,"syntology":null},{"url":"/paper/melt-towards-automated-multimodal-emotion","slug":"melt-towards-automated-multimodal-emotion","title":"MELT: Towards Automated Multimodal Emotion Data Annotation by Leveraging LLM Embedded Knowledge","date":"2025-05-30","arxiv_id":"2505.24493","repositories_listed":1,"syntology":null},{"url":"/paper/emosphere-ser-enhancing-speech-emotion","slug":"emosphere-ser-enhancing-speech-emotion","title":"EmoSphere-SER: Enhancing Speech Emotion Recognition Through Spherical Representation with Auxiliary Classification","date":"2025-05-26","arxiv_id":"2505.19693","repositories_listed":1,"syntology":null},{"url":"/paper/improving-speech-emotion-recognition-through-1","slug":"improving-speech-emotion-recognition-through-1","title":"Improving Speech Emotion Recognition Through Cross Modal Attention Alignment and Balanced Stacking Model","date":"2025-05-26","arxiv_id":"2505.20007","repositories_listed":1,"syntology":null},{"url":"/paper/abhinaya-a-system-for-speech-emotion","slug":"abhinaya-a-system-for-speech-emotion","title":"ABHINAYA -- A System for Speech Emotion Recognition In Naturalistic Conditions Challenge","date":"2025-05-23","arxiv_id":"2505.18217","repositories_listed":1,"syntology":null},{"url":"/paper/bersting-at-the-screams-a-benchmark-for","slug":"bersting-at-the-screams-a-benchmark-for","title":"BERSting at the Screams: A Benchmark for Distanced, Emotional and Shouted Speech Recognition","date":"2025-04-30","arxiv_id":"2505.00059","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-meet-contrastive","slug":"large-language-models-meet-contrastive","title":"Large Language Models Meet Contrastive Learning: Zero-Shot Emotion Recognition Across Languages","date":"2025-03-25","arxiv_id":"2503.21806","repositories_listed":1,"syntology":null},{"url":"/paper/steering-language-model-to-stable-speech","slug":"steering-language-model-to-stable-speech","title":"Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought","date":"2025-02-25","arxiv_id":"2502.18186","repositories_listed":1,"syntology":null},{"url":"/paper/sigwavnet-learning-multiresolution-signal","slug":"sigwavnet-learning-multiresolution-signal","title":"SigWavNet: Learning Multiresolution Signal Wavelet Network for Speech Emotion Recognition","date":"2025-02-01","arxiv_id":"2502.00310","repositories_listed":1,"syntology":null},{"url":"/paper/osum-advancing-open-speech-understanding","slug":"osum-advancing-open-speech-understanding","title":"OSUM: Advancing Open Speech Understanding Models with Limited Resources in Academia","date":"2025-01-23","arxiv_id":"2501.13306","repositories_listed":1,"syntology":null},{"url":"/paper/emotional-vietnamese-speech-based-depression","slug":"emotional-vietnamese-speech-based-depression","title":"Emotional Vietnamese Speech-Based Depression Diagnosis Using Dynamic Attention Mechanism","date":"2024-12-11","arxiv_id":"2412.08683","repositories_listed":1,"syntology":null},{"url":"/paper/feature-distribution-adaptation-network-for","slug":"feature-distribution-adaptation-network-for","title":"Multi-modal Speech Emotion Recognition via Feature Distribution Adaptation Network","date":"2024-10-29","arxiv_id":"2410.22023","repositories_listed":1,"syntology":null},{"url":"/paper/audio-explanation-synthesis-with-generative","slug":"audio-explanation-synthesis-with-generative","title":"Audio Explanation Synthesis with Generative Foundation Models","date":"2024-10-10","arxiv_id":"2410.07530","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-speech-emotion-recognition","slug":"cross-lingual-speech-emotion-recognition","title":"Cross-Lingual Speech Emotion Recognition: Humans vs. Self-Supervised Models","date":"2024-09-25","arxiv_id":"2409.16920","repositories_listed":1,"syntology":null},{"url":"/paper/improving-speech-emotion-recognition-in-under","slug":"improving-speech-emotion-recognition-in-under","title":"Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection","date":"2024-09-17","arxiv_id":"2409.10985","repositories_listed":1,"syntology":null},{"url":"/paper/tbdm-net-bidirectional-dense-networks-with","slug":"tbdm-net-bidirectional-dense-networks-with","title":"TBDM-Net: Bidirectional Dense Networks with Gender Information for Speech Emotion Recognition","date":"2024-09-16","arxiv_id":"2409.10056","repositories_listed":1,"syntology":null},{"url":"/paper/explaining-deep-learning-embeddings-for","slug":"explaining-deep-learning-embeddings-for","title":"Explaining Deep Learning Embeddings for Speech Emotion Recognition by Predicting Interpretable Acoustic Features","date":"2024-09-14","arxiv_id":"2409.09511","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-content-and-acoustic","slug":"leveraging-content-and-acoustic","title":"Leveraging Content and Acoustic Representations for Speech Emotion Recognition","date":"2024-09-09","arxiv_id":"2409.05566","repositories_listed":1,"syntology":null},{"url":"/paper/the-whole-is-bigger-than-the-sum-of-its-parts","slug":"the-whole-is-bigger-than-the-sum-of-its-parts","title":"The Whole Is Bigger Than the Sum of Its Parts: Modeling Individual Annotators to Capture Emotional Variability","date":"2024-08-21","arxiv_id":"2408.11956","repositories_listed":1,"syntology":null},{"url":"/paper/ser-evals-in-domain-and-out-of-domain","slug":"ser-evals-in-domain-and-out-of-domain","title":"SER Evals: In-domain and Out-of-domain Benchmarking for Speech Emotion Recognition","date":"2024-08-14","arxiv_id":"2408.07851","repositories_listed":1,"syntology":null},{"url":"/paper/bsc-upc-at-emospeech-iberlef2024-attention","slug":"bsc-upc-at-emospeech-iberlef2024-attention","title":"BSC-UPC at EmoSPeech-IberLEF2024: Attention Pooling for Emotion Recognition","date":"2024-07-17","arxiv_id":"2407.12467","repositories_listed":1,"syntology":null},{"url":"/paper/are-you-sure-analysing-uncertainty","slug":"are-you-sure-analysing-uncertainty","title":"Are you sure? Analysing Uncertainty Quantification Approaches for Real-world Speech Emotion Recognition","date":"2024-07-01","arxiv_id":"2407.01143","repositories_listed":1,"syntology":null},{"url":"/paper/odyssey-2024-speech-emotion-recognition","slug":"odyssey-2024-speech-emotion-recognition","title":"Odyssey 2024 - Speech Emotion Recognition Challenge: Dataset, Baseline Framework, and Results","date":"2024-06-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/exploring-multilingual-unseen-speaker-emotion","slug":"exploring-multilingual-unseen-speaker-emotion","title":"Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-Attention Cues in Multitask Learning","date":"2024-06-13","arxiv_id":"2406.08931","repositories_listed":1,"syntology":null},{"url":"/paper/speech-emotion-recognition-with-asr","slug":"speech-emotion-recognition-with-asr","title":"Speech Emotion Recognition with ASR Transcripts: A Comprehensive Study on Word Error Rate and Fusion Techniques","date":"2024-06-12","arxiv_id":"2406.08353","repositories_listed":1,"syntology":null},{"url":"/paper/emobox-multilingual-multi-corpus-speech","slug":"emobox-multilingual-multi-corpus-speech","title":"EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark","date":"2024-06-11","arxiv_id":"2406.07162","repositories_listed":1,"syntology":null},{"url":"/paper/exhubert-enhancing-hubert-through-block","slug":"exhubert-enhancing-hubert-through-block","title":"ExHuBERT: Enhancing HuBERT Through Block Extension and Fine-Tuning on 37 Emotion Datasets","date":"2024-06-11","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/enrolment-based-personalisation-for-improving","slug":"enrolment-based-personalisation-for-improving","title":"Enrolment-based personalisation for improving individual-level fairness in speech emotion recognition","date":"2024-06-10","arxiv_id":"2406.06665","repositories_listed":1,"syntology":null},{"url":"/paper/interspeech-2009-emotion-challenge-revisited","slug":"interspeech-2009-emotion-challenge-revisited","title":"INTERSPEECH 2009 Emotion Challenge Revisited: Benchmarking 15 Years of Progress in Speech Emotion Recognition","date":"2024-06-10","arxiv_id":"2406.06401","repositories_listed":1,"syntology":null},{"url":"/paper/blsp-emo-towards-empathetic-large-speech","slug":"blsp-emo-towards-empathetic-large-speech","title":"BLSP-Emo: Towards Empathetic Large Speech-Language Models","date":"2024-06-06","arxiv_id":"2406.03872","repositories_listed":1,"syntology":{"n":8,"n_ran":7,"n_constructed":0,"n_ran_checked":4,"n_instrument":3,"n_unverified":1,"n_honours":3,"n_violates":0,"n_no_contract":1,"n_pointer_only":3,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/blsp-emo-towards-empathetic-large-speech#ran","syntology_url":"https://syntology.ai/paper/2406.03872","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03872"}},"official":{"repos":["cwang621/blsp-emo"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/iterative-feature-boosting-for-explainable-1","slug":"iterative-feature-boosting-for-explainable-1","title":"Iterative Feature Boosting for Explainable Speech Emotion Recognition","date":"2024-05-30","arxiv_id":"2405.20172","repositories_listed":1,"syntology":null},{"url":"/paper/crossmodal-asr-error-correction-with-discrete","slug":"crossmodal-asr-error-correction-with-discrete","title":"Crossmodal ASR Error Correction with Discrete Speech Units","date":"2024-05-26","arxiv_id":"2405.16677","repositories_listed":1,"syntology":null},{"url":"/paper/fine-grained-speech-sentiment-analysis-in","slug":"fine-grained-speech-sentiment-analysis-in","title":"Fine-grained Speech Sentiment Analysis in Chinese Psychological Support Hotlines Based on Large-scale Pre-trained Model","date":"2024-05-07","arxiv_id":"2405.04128","repositories_listed":1,"syntology":null},{"url":"/paper/a-systematic-evaluation-of-adversarial","slug":"a-systematic-evaluation-of-adversarial","title":"A Systematic Evaluation of Adversarial Attacks against Speech Emotion Recognition Models","date":"2024-04-29","arxiv_id":"2404.18514","repositories_listed":1,"syntology":null},{"url":"/paper/nemo-dataset-of-emotional-speech-in-polish","slug":"nemo-dataset-of-emotional-speech-in-polish","title":"nEMO: Dataset of Emotional Speech in Polish","date":"2024-04-09","arxiv_id":"2404.06292","repositories_listed":1,"syntology":null},{"url":"/paper/accuracy-enhancement-method-for-speech","slug":"accuracy-enhancement-method-for-speech","title":"Accuracy enhancement method for speech emotion recognition from spectrogram using temporal frequency correlation and positional information learning through knowledge transfer","date":"2024-03-26","arxiv_id":"2403.17327","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-the-emotional-states-of-high-risk","slug":"unlocking-the-emotional-states-of-high-risk","title":"Unlocking the Emotional States of High-Risk Suicide Callers through Speech Analysis","date":"2024-03-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/emodarts-joint-optimisation-of-cnn-sequential","slug":"emodarts-joint-optimisation-of-cnn-sequential","title":"emoDARTS: Joint Optimisation of CNN & Sequential Neural Network Architectures for Superior Speech Emotion Recognition","date":"2024-03-21","arxiv_id":"2403.14083","repositories_listed":1,"syntology":null},{"url":"/paper/speech-emotion-recognition-via-cnn","slug":"speech-emotion-recognition-via-cnn","title":"Speech Emotion Recognition Via CNN-Transformer and Multidimensional Attention Mechanism","date":"2024-03-07","arxiv_id":"2403.04743","repositories_listed":1,"syntology":null},{"url":"/paper/speech-emotion-recognition-from-voice","slug":"speech-emotion-recognition-from-voice","title":"EMOVOME: A Dataset for Emotion Recognition in Spontaneous Real-Life Speech","date":"2024-03-04","arxiv_id":"2403.02167","repositories_listed":1,"syntology":null},{"url":"/paper/emo-superb-an-in-depth-look-at-speech-emotion","slug":"emo-superb-an-in-depth-look-at-speech-emotion","title":"EMO-SUPERB: An In-depth Look at Speech Emotion Recognition","date":"2024-02-20","arxiv_id":"2402.13018","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":0,"n_ran_checked":3,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/emo-superb-an-in-depth-look-at-speech-emotion#ran","syntology_url":"https://syntology.ai/paper/2402.13018","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2402.13018"}},"official":{"repos":["EMOsuperb/EMO-SUPERB-submission"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/filter-based-multi-task-cross-corpus-feature","slug":"filter-based-multi-task-cross-corpus-feature","title":"Filter-based multi-task cross-corpus feature learning for speech emotion recognition","date":"2024-02-20","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/frame-level-emotional-state-alignment-method","slug":"frame-level-emotional-state-alignment-method","title":"Frame-level emotional state alignment method for speech emotion recognition","date":"2023-12-27","arxiv_id":"2312.16383","repositories_listed":1,"syntology":null},{"url":"/paper/an-extended-variational-mode-decomposition-1","slug":"an-extended-variational-mode-decomposition-1","title":"An Extended Variational Mode Decomposition Algorithm Developed Speech Emotion Recognition Performance","date":"2023-12-18","arxiv_id":"2312.10937","repositories_listed":1,"syntology":null},{"url":"/paper/leveraged-mel-spectrograms-using-harmonic-and-1","slug":"leveraged-mel-spectrograms-using-harmonic-and-1","title":"Leveraged Mel spectrograms using Harmonic and Percussive Components in Speech Emotion Recognition","date":"2023-12-18","arxiv_id":"2312.10949","repositories_listed":1,"syntology":null},{"url":"/paper/pre-trained-speech-processing-models-contain","slug":"pre-trained-speech-processing-models-contain","title":"Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition","date":"2023-10-29","arxiv_id":"2310.18877","repositories_listed":1,"syntology":null},{"url":"/paper/decoding-emotions-a-comprehensive","slug":"decoding-emotions-a-comprehensive","title":"Decoding Emotions: A comprehensive Multilingual Study of Speech Models for Speech Emotion Recognition","date":"2023-08-17","arxiv_id":"2308.08713","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":2,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/decoding-emotions-a-comprehensive#ran","syntology_url":"https://syntology.ai/paper/2308.08713","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.08713"}},"official":{"repos":["95anantsingh/decoding-emotions"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/do-you-remember-overcoming-catastrophic","slug":"do-you-remember-overcoming-catastrophic","title":"Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection","date":"2023-08-07","arxiv_id":"2308.03300","repositories_listed":1,"syntology":{"n":5,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/do-you-remember-overcoming-catastrophic#ran","syntology_url":"https://syntology.ai/paper/2308.03300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.03300"}},"official":{"repos":["cecile-hi/regularized-adaptive-weight-modification"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/emo-dna-emotion-decoupling-and-alignment","slug":"emo-dna-emotion-decoupling-and-alignment","title":"Emo-DNA: Emotion Decoupling and Alignment Learning for Cross-Corpus Speech Emotion Recognition","date":"2023-08-04","arxiv_id":"2308.02190","repositories_listed":1,"syntology":null},{"url":"/paper/a-change-of-heart-improving-speech-emotion","slug":"a-change-of-heart-improving-speech-emotion","title":"A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality Conversion","date":"2023-07-21","arxiv_id":"2307.11584","repositories_listed":1,"syntology":null},{"url":"/paper/vesper-a-compact-and-effective-pretrained","slug":"vesper-a-compact-and-effective-pretrained","title":"Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition","date":"2023-07-20","arxiv_id":"2307.10757","repositories_listed":1,"syntology":null},{"url":"/paper/cross-lingual-cross-age-group-adaptation-for","slug":"cross-lingual-cross-age-group-adaptation-for","title":"Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition","date":"2023-06-26","arxiv_id":"2306.14517","repositories_listed":1,"syntology":null},{"url":"/paper/improving-speech-emotion-recognition","slug":"improving-speech-emotion-recognition","title":"Enhancing Speech Emotion Recognition Through Differentiable Architecture Search","date":"2023-05-23","arxiv_id":"2305.14402","repositories_listed":1,"syntology":null},{"url":"/paper/learning-robust-self-attention-features-for","slug":"learning-robust-self-attention-features-for","title":"Learning Robust Self-attention Features for Speech Emotion Recognition with Label-adaptive Mixup","date":"2023-05-07","arxiv_id":"2305.06273","repositories_listed":1,"syntology":null},{"url":"/paper/a-multimodal-dynamical-variational","slug":"a-multimodal-dynamical-variational","title":"A multimodal dynamical variational autoencoder for audiovisual speech representation learning","date":"2023-05-05","arxiv_id":"2305.03582","repositories_listed":1,"syntology":null},{"url":"/paper/a-vector-quantized-masked-autoencoder-for","slug":"a-vector-quantized-masked-autoencoder-for","title":"A vector quantized masked autoencoder for speech emotion recognition","date":"2023-04-21","arxiv_id":"2304.11117","repositories_listed":1,"syntology":null},{"url":"/paper/dwformer-dynamic-window-transformer-for","slug":"dwformer-dynamic-window-transformer-for","title":"DWFormer: Dynamic Window transFormer for Speech Emotion Recognition","date":"2023-03-03","arxiv_id":"2303.01694","repositories_listed":1,"syntology":null},{"url":"/paper/low-latency-transformers-for-speech","slug":"low-latency-transformers-for-speech","title":"A low latency attention module for streaming self-supervised speech representation learning","date":"2023-02-27","arxiv_id":"2302.13451","repositories_listed":1,"syntology":null},{"url":"/paper/speechformer-a-hierarchical-efficient-1","slug":"speechformer-a-hierarchical-efficient-1","title":"SpeechFormer++: A Hierarchical Efficient Framework for Paralinguistic Speech Processing","date":"2023-02-27","arxiv_id":"2302.14638","repositories_listed":1,"syntology":null},{"url":"/paper/emogator-a-new-open-source-vocal-burst","slug":"emogator-a-new-open-source-vocal-burst","title":"EmoGator: A New Open Source Vocal Burst Dataset with Baseline Machine Learning Classification Methodologies","date":"2023-01-02","arxiv_id":"2301.00508","repositories_listed":1,"syntology":null},{"url":"/paper/a-speech-corpus-of-quechua-collao-for","slug":"a-speech-corpus-of-quechua-collao-for","title":"A speech corpus of Quechua Collao for automatic dimensional emotion recognition","date":"2022-12-24","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/large-raw-emotional-dataset-with-aggregation","slug":"large-raw-emotional-dataset-with-aggregation","title":"Large Raw Emotional Dataset with Aggregation Mechanism","date":"2022-12-23","arxiv_id":"2212.12266","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/large-raw-emotional-dataset-with-aggregation#ran","syntology_url":"https://syntology.ai/paper/2212.12266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.12266"}},"official":{"repos":["salute-developers/golos"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["unlocated"]}}},{"url":"/paper/leveraging-pre-trained-acoustic-feature","slug":"leveraging-pre-trained-acoustic-feature","title":"Leveraging Pre-Trained Acoustic Feature Extractor For Affective Vocal Bursts Tasks","date":"2022-12-21","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/temporal-modeling-matters-a-novel-temporal","slug":"temporal-modeling-matters-a-novel-temporal","title":"Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech Emotion Recognition","date":"2022-11-14","arxiv_id":"2211.08233","repositories_listed":1,"syntology":null},{"url":"/paper/speaker-vgg-cct-cross-corpus-speech-emotion","slug":"speaker-vgg-cct-cross-corpus-speech-emotion","title":"SPEAKER VGG CCT: Cross-corpus Speech Emotion Recognition with Speaker Embedding and Vision Transformers","date":"2022-11-04","arxiv_id":"2211.02366","repositories_listed":1,"syntology":null},{"url":"/paper/gm-tcnet-gated-multi-scale-temporal","slug":"gm-tcnet-gated-multi-scale-temporal","title":"GM-TCNet: Gated Multi-scale Temporal Convolutional Network using Emotion Causality for Speech Emotion Recognition","date":"2022-10-28","arxiv_id":"2210.15834","repositories_listed":1,"syntology":null},{"url":"/paper/knowledge-transfer-for-on-device-speech","slug":"knowledge-transfer-for-on-device-speech","title":"Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured Learning","date":"2022-10-26","arxiv_id":"2210.14977","repositories_listed":1,"syntology":null},{"url":"/paper/pretrained-audio-neural-networks-for-speech","slug":"pretrained-audio-neural-networks-for-speech","title":"Pretrained audio neural networks for Speech emotion recognition in Portuguese","date":"2022-10-26","arxiv_id":"2210.14716","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-label-uncertainty-modeling-in","slug":"end-to-end-label-uncertainty-modeling-in","title":"End-to-End Label Uncertainty Modeling in Speech Emotion Recognition using Bayesian Neural Networks and Label Distribution Learning","date":"2022-09-30","arxiv_id":"2209.15449","repositories_listed":1,"syntology":null},{"url":"/paper/domain-specific-wav2vec-2-0-fine-tuning-for","slug":"domain-specific-wav2vec-2-0-fine-tuning-for","title":"Domain Specific Wav2vec 2.0 Fine-tuning For The SE&R 2022 Challenge","date":"2022-07-29","arxiv_id":"2207.14418","repositories_listed":1,"syntology":null},{"url":"/paper/label-uncertainty-modeling-and-prediction-for","slug":"label-uncertainty-modeling-and-prediction-for","title":"Label Uncertainty Modeling and Prediction for Speech Emotion Recognition using t-Distributions","date":"2022-07-25","arxiv_id":"2207.12135","repositories_listed":1,"syntology":null},{"url":"/paper/analysis-of-self-supervised-learning-and","slug":"analysis-of-self-supervised-learning-and","title":"Analysis of Self-Supervised Learning and Dimensionality Reduction Methods in Clustering-Based Active Learning for Speech Emotion Recognition","date":"2022-06-21","arxiv_id":"2206.10188","repositories_listed":1,"syntology":null},{"url":"/paper/lerac-learning-rate-curriculum","slug":"lerac-learning-rate-curriculum","title":"Learning Rate Curriculum","date":"2022-05-18","arxiv_id":"2205.09180","repositories_listed":1,"syntology":null},{"url":"/paper/speech-emotion-recognition-with-global-aware","slug":"speech-emotion-recognition-with-global-aware","title":"Speech Emotion Recognition with Global-Aware Fusion on Multi-scale Feature Representation","date":"2022-04-12","arxiv_id":"2204.05571","repositories_listed":1,"syntology":null},{"url":"/paper/learning-speech-emotion-representations-in","slug":"learning-speech-emotion-representations-in","title":"Learning Speech Emotion Representations in the Quaternion Domain","date":"2022-04-05","arxiv_id":"2204.02385","repositories_listed":1,"syntology":null},{"url":"/paper/mmer-multimodal-multi-task-learning-for","slug":"mmer-multimodal-multi-task-learning-for","title":"MMER: Multimodal Multi-task Learning for Speech Emotion Recognition","date":"2022-03-31","arxiv_id":"2203.16794","repositories_listed":1,"syntology":null},{"url":"/paper/speech-emotion-recognition-with-co-attention","slug":"speech-emotion-recognition-with-co-attention","title":"Speech Emotion Recognition with Co-Attention based Multi-level Acoustic Information","date":"2022-03-29","arxiv_id":"2203.15326","repositories_listed":1,"syntology":null},{"url":"/paper/a-dataset-for-speech-emotion-recognition-in","slug":"a-dataset-for-speech-emotion-recognition-in","title":"A Dataset for Speech Emotion Recognition in Greek Theatrical Plays","date":"2022-03-27","arxiv_id":"2203.15568","repositories_listed":1,"syntology":null},{"url":"/paper/towards-privacy-preserving-speech","slug":"towards-privacy-preserving-speech","title":"A Speech Representation Anonymization Framework via Selective Noise Perturbation","date":"2022-03-26","arxiv_id":"2203.14171","repositories_listed":1,"syntology":null},{"url":"/paper/septr-separable-transformer-for-audio","slug":"septr-separable-transformer-for-audio","title":"SepTr: Separable Transformer for Audio Spectrogram Processing","date":"2022-03-17","arxiv_id":"2203.09581","repositories_listed":1,"syntology":null},{"url":"/paper/semi-fedser-semi-supervised-learning-for","slug":"semi-fedser-semi-supervised-learning-for","title":"Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling","date":"2022-03-15","arxiv_id":"2203.08810","repositories_listed":1,"syntology":null}],"syntology_records":12,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/speech-emotion-recognition-on-iemocap","since_archive":"/sota/speech-emotion-recognition-on-iemocap#since-judged","papers_judged":1,"placed":0},{"leaderboard":"/sota/speech-emotion-recognition-on-shemo","since_archive":"/sota/speech-emotion-recognition-on-shemo#since-judged","papers_judged":1,"placed":0}]},"papers_where_code_ran":15,"papers_where_code_ran_first_page":"/task/speech-emotion-recognition/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":5,"url":"/task/speech-emotion-recognition/papers/2","json":"/task/speech-emotion-recognition/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/speech-emotion-recognition/papers/3","json":"/task/speech-emotion-recognition/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/speech-emotion-recognition/papers/4","json":"/task/speech-emotion-recognition/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/speech-emotion-recognition/papers/5","json":"/task/speech-emotion-recognition/papers/5.json","rows":31},{"order":"ran","page":1,"of":1,"url":"/task/speech-emotion-recognition/papers/ran/1","json":"/task/speech-emotion-recognition/papers/ran/1.json","rows":15}],"description_links":{"kept":1,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-10-05T00:36:11+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"},"record_sha256":"f76924b6a9e7a75a7643848a3d2d3af3f283ec160c0a56aff2faa4721298188d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}