{"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-to-text","name":"Speech-to-Text","slug":"speech-to-text","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":403,"papers_with_code":129,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/common-voice","name":"Common Voice","full_name":"Common Voice","num_papers_in_archive":449}],"subtasks":[],"parent_tasks":[],"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":403,"of_with_code":129,"tagged_in_all":403,"counts":{"archive_papers_tagged":403,"with_a_code_link":129,"where_syntology_ran_a_sample":24,"not_listed_spam_title":0,"listed":403,"listed_where_code_ran":24,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":17,"every_run_a_failure_of_syntologys_instrument":7,"listed_with_a_run_with_no_instrument_failure":17,"listed_every_run_a_failure_of_syntologys_instrument":7,"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/joint-ctc-attention-based-end-to-end-speech","slug":"joint-ctc-attention-based-end-to-end-speech","title":"Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning","date":"2016-09-21","arxiv_id":"1609.06773","repositories_listed":8,"syntology":{"n":10,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":7,"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) · 7 unverified","sample_list":"/paper/joint-ctc-attention-based-end-to-end-speech#ran","syntology_url":"https://syntology.ai/paper/1609.06773","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.06773"}},"official":null}},{"url":"/paper/clotho-an-audio-captioning-dataset","slug":"clotho-an-audio-captioning-dataset","title":"Clotho: An Audio Captioning Dataset","date":"2019-10-21","arxiv_id":"1910.09387","repositories_listed":7,"syntology":{"n":21,"n_ran":19,"n_constructed":0,"n_ran_checked":16,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":16,"n_pointer_only":5,"phrase":"19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/clotho-an-audio-captioning-dataset#ran","syntology_url":"https://syntology.ai/paper/1910.09387","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1910.09387"}},"official":null}},{"url":"/paper/fairseq-s2t-fast-speech-to-text-modeling-with","slug":"fairseq-s2t-fast-speech-to-text-modeling-with","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","date":"2020-10-11","arxiv_id":"2010.05171","repositories_listed":5,"syntology":null},{"url":"/paper/seamlessm4t-massively-multilingual-multimodal","slug":"seamlessm4t-massively-multilingual-multimodal","title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","date":"2023-08-22","arxiv_id":"2308.11596","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/seamlessm4t-massively-multilingual-multimodal#ran","syntology_url":"https://syntology.ai/paper/2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"}},"official":{"repos":["facebookresearch/seamless_communication"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/tools-and-resources-for-romanian-text-to","slug":"tools-and-resources-for-romanian-text-to","title":"Tools and resources for Romanian text-to-speech and speech-to-text applications","date":"2018-02-15","arxiv_id":"1802.05583","repositories_listed":4,"syntology":null},{"url":"/paper/tensor-comprehensions-framework-agnostic-high","slug":"tensor-comprehensions-framework-agnostic-high","title":"Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions","date":"2018-02-13","arxiv_id":"1802.04730","repositories_listed":4,"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/tensor-comprehensions-framework-agnostic-high#ran","syntology_url":"https://syntology.ai/paper/1802.04730","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.04730"}},"official":null}},{"url":"/paper/audio-adversarial-examples-targeted-attacks","slug":"audio-adversarial-examples-targeted-attacks","title":"Audio Adversarial Examples: Targeted Attacks on Speech-to-Text","date":"2018-01-05","arxiv_id":"1801.01944","repositories_listed":4,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/audio-adversarial-examples-targeted-attacks#ran","syntology_url":"https://syntology.ai/paper/1801.01944","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1801.01944"}},"official":null}},{"url":"/paper/scribosermo-fast-speech-to-text-models-for","slug":"scribosermo-fast-speech-to-text-models-for","title":"Scribosermo: Fast Speech-to-Text models for German and other Languages","date":"2021-10-15","arxiv_id":"2110.07982","repositories_listed":3,"syntology":null},{"url":"/paper/one-tts-alignment-to-rule-them-all","slug":"one-tts-alignment-to-rule-them-all","title":"One TTS Alignment To Rule Them All","date":"2021-08-23","arxiv_id":"2108.10447","repositories_listed":3,"syntology":null},{"url":"/paper/deep-reinforcement-learning-for-sequence-to","slug":"deep-reinforcement-learning-for-sequence-to","title":"Deep Reinforcement Learning For Sequence to Sequence Models","date":"2018-05-24","arxiv_id":"1805.09461","repositories_listed":3,"syntology":{"n":17,"n_ran":16,"n_constructed":0,"n_ran_checked":15,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":13,"n_pointer_only":2,"phrase":"16 ran (of which 0 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/deep-reinforcement-learning-for-sequence-to#ran","syntology_url":"https://syntology.ai/paper/1805.09461","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1805.09461"}},"official":{"repos":["yaserkl/RLSeq2Seq"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":0,"n_ran_no_instrument_failure":11,"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/speechut-bridging-speech-and-text-with-hidden","slug":"speechut-bridging-speech-and-text-with-hidden","title":"SpeechUT: Bridging Speech and Text with Hidden-Unit for Encoder-Decoder Based Speech-Text Pre-training","date":"2022-10-07","arxiv_id":"2210.03730","repositories_listed":2,"syntology":null},{"url":"/paper/finstreder-simple-and-fast-spoken-language","slug":"finstreder-simple-and-fast-spoken-language","title":"Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models","date":"2022-06-29","arxiv_id":"2206.14589","repositories_listed":2,"syntology":null},{"url":"/paper/paddlespeech-an-easy-to-use-all-in-one-speech-1","slug":"paddlespeech-an-easy-to-use-all-in-one-speech-1","title":"PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkit","date":"2022-05-20","arxiv_id":"2205.12007","repositories_listed":2,"syntology":null},{"url":"/paper/a-3-t-alignment-aware-acoustic-and-text","slug":"a-3-t-alignment-aware-acoustic-and-text","title":"A$^3$T: Alignment-Aware Acoustic and Text Pretraining for Speech Synthesis and Editing","date":"2022-03-18","arxiv_id":"2203.09690","repositories_listed":2,"syntology":{"n":7,"n_ran":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":5,"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) · 5 unverified","sample_list":"/paper/a-3-t-alignment-aware-acoustic-and-text#ran","syntology_url":"https://syntology.ai/paper/2203.09690","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09690"}},"official":null}},{"url":"/paper/learning-shared-semantic-space-for-speech-to","slug":"learning-shared-semantic-space-for-speech-to","title":"Learning Shared Semantic Space for Speech-to-Text Translation","date":"2021-05-07","arxiv_id":"2105.03095","repositories_listed":2,"syntology":{"n":7,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":7,"n_pointer_only":7,"phrase":"7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/learning-shared-semantic-space-for-speech-to#ran","syntology_url":"https://syntology.ai/paper/2105.03095","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.03095"}},"official":{"repos":["Glaciohound/Chimera-SLT","Glaciohound/Chimera-ST"],"state":"official (archive's flag): 7 ran","n_ran":7,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/covost-2-a-massively-multilingual-speech-to","slug":"covost-2-a-massively-multilingual-speech-to","title":"CoVoST 2 and Massively Multilingual Speech-to-Text Translation","date":"2020-07-20","arxiv_id":"2007.10310","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/covost-2-a-massively-multilingual-speech-to#ran","syntology_url":"https://syntology.ai/paper/2007.10310","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.10310"}},"official":{"repos":["facebookresearch/covost"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/common-voice-a-massively-multilingual-speech","slug":"common-voice-a-massively-multilingual-speech","title":"Common Voice: A Massively-Multilingual Speech Corpus","date":"2019-12-13","arxiv_id":"1912.06670","repositories_listed":2,"syntology":null},{"url":"/paper/speech-model-pre-training-for-end-to-end","slug":"speech-model-pre-training-for-end-to-end","title":"Speech Model Pre-training for End-to-End Spoken Language Understanding","date":"2019-04-07","arxiv_id":"1904.03670","repositories_listed":2,"syntology":null},{"url":"/paper/beavertalk-oregon-state-university-s-iwslt","slug":"beavertalk-oregon-state-university-s-iwslt","title":"BeaverTalk: Oregon State University's IWSLT 2025 Simultaneous Speech Translation System","date":"2025-05-29","arxiv_id":"2505.24016","repositories_listed":1,"syntology":null},{"url":"/paper/the-warmup-dilemma-how-learning-rate","slug":"the-warmup-dilemma-how-learning-rate","title":"The Warmup Dilemma: How Learning Rate Strategies Impact Speech-to-Text Model Convergence","date":"2025-05-29","arxiv_id":"2505.23420","repositories_listed":1,"syntology":null},{"url":"/paper/audio-jailbreak-attacks-exposing","slug":"audio-jailbreak-attacks-exposing","title":"Audio Jailbreak Attacks: Exposing Vulnerabilities in SpeechGPT in a White-Box Framework","date":"2025-05-24","arxiv_id":"2505.18864","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-speech-to-speech-dialogue-modeling","slug":"enhancing-speech-to-speech-dialogue-modeling","title":"Enhancing Speech-to-Speech Dialogue Modeling with End-to-End Retrieval-Augmented Generation","date":"2025-04-27","arxiv_id":"2505.00028","repositories_listed":1,"syntology":null},{"url":"/paper/medibeng-whisper-tiny-a-fine-tuned-code","slug":"medibeng-whisper-tiny-a-fine-tuned-code","title":"MEDIBENG WHISPER TINY: A FINE-TUNED CODE-SWITCHED BENGALI-ENGLISH TRANSLATOR FOR CLINICAL APPLICATIONS","date":"2025-04-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/transformer-based-named-entity-recognition-2","slug":"transformer-based-named-entity-recognition-2","title":"Transformer-Based Named Entity Recognition for Automated Server Provisioning","date":"2025-04-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/measuring-the-effect-of-transcription-noise","slug":"measuring-the-effect-of-transcription-noise","title":"Measuring the Effect of Transcription Noise on Downstream Language Understanding Tasks","date":"2025-02-19","arxiv_id":"2502.13645","repositories_listed":1,"syntology":null},{"url":"/paper/duplexmamba-enhancing-real-time-speech","slug":"duplexmamba-enhancing-real-time-speech","title":"DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities","date":"2025-02-16","arxiv_id":"2502.11123","repositories_listed":1,"syntology":null},{"url":"/paper/sparqle-speech-queries-to-text-translation","slug":"sparqle-speech-queries-to-text-translation","title":"SparQLe: Speech Queries to Text Translation Through LLMs","date":"2025-02-13","arxiv_id":"2502.09284","repositories_listed":1,"syntology":null},{"url":"/paper/high-fidelity-simultaneous-speech-to-speech","slug":"high-fidelity-simultaneous-speech-to-speech","title":"High-Fidelity Simultaneous Speech-To-Speech Translation","date":"2025-02-05","arxiv_id":"2502.03382","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/whispa-semantically-and-psychologically","slug":"whispa-semantically-and-psychologically","title":"WhiSPA: Semantically and Psychologically Aligned Whisper with Self-Supervised Contrastive and Student-Teacher Learning","date":"2025-01-15","arxiv_id":"2501.16344","repositories_listed":1,"syntology":null},{"url":"/paper/fleurs-slu-a-massively-multilingual-benchmark","slug":"fleurs-slu-a-massively-multilingual-benchmark","title":"Fleurs-SLU: A Massively Multilingual Benchmark for Spoken Language Understanding","date":"2025-01-10","arxiv_id":"2501.06117","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-whisper-on-low-resource-languages","slug":"fine-tuning-whisper-on-low-resource-languages","title":"Fine-tuning Whisper on Low-Resource Languages for Real-World Applications","date":"2024-12-20","arxiv_id":"2412.15726","repositories_listed":1,"syntology":null},{"url":"/paper/spes-spectrogram-perturbation-for-explainable","slug":"spes-spectrogram-perturbation-for-explainable","title":"SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generation","date":"2024-11-03","arxiv_id":"2411.01710","repositories_listed":1,"syntology":null},{"url":"/paper/sttatts-unified-speech-to-text-and-text-to","slug":"sttatts-unified-speech-to-text-and-text-to","title":"STTATTS: Unified Speech-To-Text And Text-To-Speech Model","date":"2024-10-24","arxiv_id":"2410.18607","repositories_listed":1,"syntology":null},{"url":"/paper/denial-of-service-poisoning-attacks-against","slug":"denial-of-service-poisoning-attacks-against","title":"Denial-of-Service Poisoning Attacks against Large Language Models","date":"2024-10-14","arxiv_id":"2410.10760","repositories_listed":1,"syntology":{"n":9,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":6,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":9,"phrase":"3 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; 3 where Syntology's instrument failed) · 6 unverified","sample_list":"/paper/denial-of-service-poisoning-attacks-against#ran","syntology_url":"https://syntology.ai/paper/2410.10760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.10760"}},"official":{"repos":["sail-sg/p-dos"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":6,"ran_from_kinds":["official"]}}},{"url":"/paper/optimizing-rare-word-accuracy-in-direct","slug":"optimizing-rare-word-accuracy-in-direct","title":"Optimizing Rare Word Accuracy in Direct Speech Translation with a Retrieval-and-Demonstration Approach","date":"2024-09-13","arxiv_id":"2409.09009","repositories_listed":1,"syntology":null},{"url":"/paper/openomni-a-collaborative-open-source-tool-for","slug":"openomni-a-collaborative-open-source-tool-for","title":"OpenOmni: A Collaborative Open Source Tool for Building Future-Ready Multimodal Conversational Agents","date":"2024-08-06","arxiv_id":"2408.03047","repositories_listed":1,"syntology":null},{"url":"/paper/llast-improved-end-to-end-speech-translation","slug":"llast-improved-end-to-end-speech-translation","title":"LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models","date":"2024-07-22","arxiv_id":"2407.15415","repositories_listed":1,"syntology":null},{"url":"/paper/covoswitch-machine-translation-of-synthetic","slug":"covoswitch-machine-translation-of-synthetic","title":"CoVoSwitch: Machine Translation of Synthetic Code-Switched Text Based on Intonation Units","date":"2024-07-19","arxiv_id":"2407.14295","repositories_listed":1,"syntology":null},{"url":"/paper/indoor-air-quality-dataset-with-activities-of","slug":"indoor-air-quality-dataset-with-activities-of","title":"Indoor Air Quality Dataset with Activities of Daily Living in Low to Middle-income Communities","date":"2024-07-19","arxiv_id":"2407.14501","repositories_listed":1,"syntology":null},{"url":"/paper/listen-and-speak-fairly-a-study-on-semantic","slug":"listen-and-speak-fairly-a-study-on-semantic","title":"Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models","date":"2024-07-09","arxiv_id":"2407.06957","repositories_listed":1,"syntology":null},{"url":"/paper/calibrated-svm-for-probabilistic","slug":"calibrated-svm-for-probabilistic","title":"Calibrated SVM for Probabilistic Classification of In-Vehicle Voices into Vehicle Commands via Voice-to-Text LLM Transformation","date":"2024-06-28","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/voices-unheard-nlp-resources-and-models-for","slug":"voices-unheard-nlp-resources-and-models-for","title":"Voices Unheard: NLP Resources and Models for Yorùbá Regional Dialects","date":"2024-06-27","arxiv_id":"2406.19564","repositories_listed":1,"syntology":null},{"url":"/paper/arzen-llm-code-switched-egyptian-arabic","slug":"arzen-llm-code-switched-egyptian-arabic","title":"ArzEn-LLM: Code-Switched Egyptian Arabic-English Translation and Speech Recognition Using LLMs","date":"2024-06-26","arxiv_id":"2406.18120","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-speech-recognition-for-the-nepali","slug":"automatic-speech-recognition-for-the-nepali","title":"Automatic speech recognition for the Nepali language using CNN, bidirectional LSTM and ResNet","date":"2024-06-25","arxiv_id":"2406.17825","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-interpolation-augmentation-for","slug":"revisiting-interpolation-augmentation-for","title":"Revisiting Interpolation Augmentation for Speech-to-Text Generation","date":"2024-06-22","arxiv_id":"2406.15846","repositories_listed":1,"syntology":null},{"url":"/paper/simulseamless-fbk-at-iwslt-2024-simultaneous","slug":"simulseamless-fbk-at-iwslt-2024-simultaneous","title":"SimulSeamless: FBK at IWSLT 2024 Simultaneous Speech Translation","date":"2024-06-20","arxiv_id":"2406.14177","repositories_listed":1,"syntology":null},{"url":"/paper/whisper-flamingo-integrating-visual-features","slug":"whisper-flamingo-integrating-visual-features","title":"Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation","date":"2024-06-14","arxiv_id":"2406.10082","repositories_listed":1,"syntology":{"n":18,"n_ran":11,"n_constructed":0,"n_ran_checked":8,"n_instrument":3,"n_unverified":7,"n_honours":5,"n_violates":1,"n_no_contract":2,"n_pointer_only":18,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 5 honoured, 1 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/whisper-flamingo-integrating-visual-features#ran","syntology_url":"https://syntology.ai/paper/2406.10082","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.10082"}},"official":{"repos":["roudimit/whisper-flamingo"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/a-non-autoregressive-generation-framework-for","slug":"a-non-autoregressive-generation-framework-for","title":"A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Speech Translation","date":"2024-06-11","arxiv_id":"2406.06937","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"2 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/a-non-autoregressive-generation-framework-for#ran","syntology_url":"https://syntology.ai/paper/2406.06937","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.06937"}},"official":{"repos":["ictnlp/nast-s2x"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/streamatt-direct-streaming-speech-to-text","slug":"streamatt-direct-streaming-speech-to-text","title":"StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selection","date":"2024-06-10","arxiv_id":"2406.06097","repositories_listed":1,"syntology":null},{"url":"/paper/leapformer-enabling-linear-transformers-for","slug":"leapformer-enabling-linear-transformers-for","title":"LeaPformer: Enabling Linear Transformers for Autoregressive and Simultaneous Tasks via Learned Proportions","date":"2024-05-18","arxiv_id":"2405.13046","repositories_listed":1,"syntology":{"n":4,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"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) · 2 unverified","sample_list":"/paper/leapformer-enabling-linear-transformers-for#ran","syntology_url":"https://syntology.ai/paper/2405.13046","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2405.13046"}},"official":{"repos":["osu-starlab/leapformer"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/brilla-ai-ai-contestant-for-the-national","slug":"brilla-ai-ai-contestant-for-the-national","title":"Brilla AI: AI Contestant for the National Science and Maths Quiz","date":"2024-03-04","arxiv_id":"2403.01699","repositories_listed":1,"syntology":null},{"url":"/paper/owsm-ctc-an-open-encoder-only-speech","slug":"owsm-ctc-an-open-encoder-only-speech","title":"OWSM-CTC: An Open Encoder-Only Speech Foundation Model for Speech Recognition, Translation, and Language Identification","date":"2024-02-20","arxiv_id":"2402.12654","repositories_listed":1,"syntology":null},{"url":"/paper/pushing-the-limits-of-zero-shot-end-to-end","slug":"pushing-the-limits-of-zero-shot-end-to-end","title":"Pushing the Limits of Zero-shot End-to-End Speech Translation","date":"2024-02-16","arxiv_id":"2402.10422","repositories_listed":1,"syntology":null},{"url":"/paper/careless-whisper-speech-to-text-hallucination","slug":"careless-whisper-speech-to-text-hallucination","title":"Careless Whisper: Speech-to-Text Hallucination Harms","date":"2024-02-12","arxiv_id":"2402.08021","repositories_listed":1,"syntology":null},{"url":"/paper/streaming-sequence-transduction-through","slug":"streaming-sequence-transduction-through","title":"Streaming Sequence Transduction through Dynamic Compression","date":"2024-02-02","arxiv_id":"2402.01172","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-large-multimodal-models-against","slug":"benchmarking-large-multimodal-models-against","title":"Benchmarking Large Multimodal Models against Common Corruptions","date":"2024-01-22","arxiv_id":"2401.11943","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 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; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-large-multimodal-models-against#ran","syntology_url":"https://syntology.ai/paper/2401.11943","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.11943"}},"official":{"repos":["sail-sg/mmcbench"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/funnynet-w-multimodal-learning-of-funny","slug":"funnynet-w-multimodal-learning-of-funny","title":"FunnyNet-W: Multimodal Learning of Funny Moments in Videos in the Wild","date":"2024-01-08","arxiv_id":"2401.04210","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-zero-shot-generalizability-on","slug":"investigating-zero-shot-generalizability-on","title":"Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision","date":"2023-12-30","arxiv_id":"2401.00273","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-single-channel-speaker-turn-aware","slug":"end-to-end-single-channel-speaker-turn-aware","title":"End-to-End Single-Channel Speaker-Turn Aware Conversational Speech Translation","date":"2023-11-01","arxiv_id":"2311.00697","repositories_listed":1,"syntology":null},{"url":"/paper/salm-speech-augmented-language-model-with-in","slug":"salm-speech-augmented-language-model-with-in","title":"SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translation","date":"2023-10-13","arxiv_id":"2310.09424","repositories_listed":1,"syntology":null},{"url":"/paper/an-empirical-study-of-consistency","slug":"an-empirical-study-of-consistency","title":"An Empirical Study of Consistency Regularization for End-to-End Speech-to-Text Translation","date":"2023-08-28","arxiv_id":"2308.14482","repositories_listed":1,"syntology":null},{"url":"/paper/sentence-level-multimodal-and-language","slug":"sentence-level-multimodal-and-language","title":"SONAR: Sentence-Level Multimodal and Language-Agnostic Representations","date":"2023-08-22","arxiv_id":"2308.11466","repositories_listed":1,"syntology":null},{"url":"/paper/towards-an-ai-to-win-ghana-s-national-science","slug":"towards-an-ai-to-win-ghana-s-national-science","title":"Towards an AI to Win Ghana's National Science and Maths Quiz","date":"2023-08-08","arxiv_id":"2308.04333","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/towards-an-ai-to-win-ghana-s-national-science#ran","syntology_url":"https://syntology.ai/paper/2308.04333","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.04333"}},"official":{"repos":["nsmq-ai/nsmqai"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/let-s-give-a-voice-to-conversational-agents","slug":"let-s-give-a-voice-to-conversational-agents","title":"Let's Give a Voice to Conversational Agents in Virtual Reality","date":"2023-08-04","arxiv_id":"2308.02665","repositories_listed":1,"syntology":null},{"url":"/paper/code-switched-urdu-asr-for-noisy-telephonic","slug":"code-switched-urdu-asr-for-noisy-telephonic","title":"Code-Switched Urdu ASR for Noisy Telephonic Environment using Data Centric Approach with Hybrid HMM and CNN-TDNN","date":"2023-07-24","arxiv_id":"2307.12759","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/towards-end-to-end-speech-to-text","slug":"towards-end-to-end-speech-to-text","title":"Towards End-to-end Speech-to-text Summarization","date":"2023-06-06","arxiv_id":"2306.05432","repositories_listed":1,"syntology":null},{"url":"/paper/comsl-a-composite-speech-language-model-for-1","slug":"comsl-a-composite-speech-language-model-for-1","title":"ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation","date":"2023-05-24","arxiv_id":"2305.14838","repositories_listed":1,"syntology":null},{"url":"/paper/dub-discrete-unit-back-translation-for-speech","slug":"dub-discrete-unit-back-translation-for-speech","title":"DUB: Discrete Unit Back-translation for Speech Translation","date":"2023-05-19","arxiv_id":"2305.11411","repositories_listed":1,"syntology":null},{"url":"/paper/a-whisper-transformer-for-audio-captioning","slug":"a-whisper-transformer-for-audio-captioning","title":"A Whisper transformer for audio captioning trained with synthetic captions and transfer learning","date":"2023-05-15","arxiv_id":"2305.09690","repositories_listed":1,"syntology":null},{"url":"/paper/back-translation-for-speech-to-text","slug":"back-translation-for-speech-to-text","title":"Back Translation for Speech-to-text Translation Without Transcripts","date":"2023-05-15","arxiv_id":"2305.08709","repositories_listed":1,"syntology":null},{"url":"/paper/espnet-st-v2-multipurpose-spoken-language","slug":"espnet-st-v2-multipurpose-spoken-language","title":"ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit","date":"2023-04-10","arxiv_id":"2304.04596","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/espnet-st-v2-multipurpose-spoken-language#ran","syntology_url":"https://syntology.ai/paper/2304.04596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.04596"}},"official":{"repos":["espnet/espnet"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/muavic-a-multilingual-audio-visual-corpus-for","slug":"muavic-a-multilingual-audio-visual-corpus-for","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","date":"2023-03-01","arxiv_id":"2303.00628","repositories_listed":1,"syntology":null},{"url":"/paper/psst-prosodic-speech-segmentation-with","slug":"psst-prosodic-speech-segmentation-with","title":"PSST! Prosodic Speech Segmentation with Transformers","date":"2023-02-03","arxiv_id":"2302.01984","repositories_listed":1,"syntology":null},{"url":"/paper/pre-training-for-speech-translation-ctc-meets","slug":"pre-training-for-speech-translation-ctc-meets","title":"Pre-training for Speech Translation: CTC Meets Optimal Transport","date":"2023-01-27","arxiv_id":"2301.11716","repositories_listed":1,"syntology":null},{"url":"/paper/waco-word-aligned-contrastive-learning-for","slug":"waco-word-aligned-contrastive-learning-for","title":"WACO: Word-Aligned Contrastive Learning for Speech Translation","date":"2022-12-19","arxiv_id":"2212.09359","repositories_listed":1,"syntology":null},{"url":"/paper/mmspeech-multi-modal-multi-task-encoder","slug":"mmspeech-multi-modal-multi-task-encoder","title":"MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition","date":"2022-11-29","arxiv_id":"2212.00500","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-speech-translation-with-dynamic","slug":"efficient-speech-translation-with-dynamic","title":"Efficient Speech Translation with Dynamic Latent Perceivers","date":"2022-10-28","arxiv_id":"2210.16264","repositories_listed":1,"syntology":null},{"url":"/paper/don-t-discard-fixed-window-audio-segmentation","slug":"don-t-discard-fixed-window-audio-segmentation","title":"Don't Discard Fixed-Window Audio Segmentation in Speech-to-Text Translation","date":"2022-10-24","arxiv_id":"2210.13363","repositories_listed":1,"syntology":null},{"url":"/paper/information-transport-based-policy-for","slug":"information-transport-based-policy-for","title":"Information-Transport-based Policy for Simultaneous Translation","date":"2022-10-22","arxiv_id":"2210.12357","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_constructed":2,"n_ran_checked":2,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":5,"phrase":"5 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/information-transport-based-policy-for#ran","syntology_url":"https://syntology.ai/paper/2210.12357","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.12357"}},"official":{"repos":["ictnlp/itst"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":2,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/anonymizing-speech-with-generative","slug":"anonymizing-speech-with-generative","title":"Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacy","date":"2022-10-13","arxiv_id":"2210.07002","repositories_listed":1,"syntology":null},{"url":"/paper/joeys2t-minimalistic-speech-to-text-modeling","slug":"joeys2t-minimalistic-speech-to-text-modeling","title":"JoeyS2T: Minimalistic Speech-to-Text Modeling with JoeyNMT","date":"2022-10-05","arxiv_id":"2210.02545","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"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) · 0 unverified","sample_list":"/paper/joeys2t-minimalistic-speech-to-text-modeling#ran","syntology_url":"https://syntology.ai/paper/2210.02545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.02545"}},"official":{"repos":["may-/joeys2t"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/m-adapter-modality-adaptation-for-end-to-end","slug":"m-adapter-modality-adaptation-for-end-to-end","title":"M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation","date":"2022-07-03","arxiv_id":"2207.00952","repositories_listed":1,"syntology":null},{"url":"/paper/revisiting-end-to-end-speech-to-text","slug":"revisiting-end-to-end-speech-to-text","title":"Revisiting End-to-End Speech-to-Text Translation From Scratch","date":"2022-06-09","arxiv_id":"2206.04571","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/revisiting-end-to-end-speech-to-text#ran","syntology_url":"https://syntology.ai/paper/2206.04571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.04571"}},"official":{"repos":["bzhangGo/zero"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/cross-modal-contrastive-learning-for-speech-1","slug":"cross-modal-contrastive-learning-for-speech-1","title":"Cross-modal Contrastive Learning for Speech Translation","date":"2022-05-05","arxiv_id":"2205.02444","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":2,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":3,"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) · 0 unverified","sample_list":"/paper/cross-modal-contrastive-learning-for-speech-1#ran","syntology_url":"https://syntology.ai/paper/2205.02444","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.02444"}},"official":{"repos":["reneeye/const"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/wav2seq-pre-training-speech-to-text-encoder","slug":"wav2seq-pre-training-speech-to-text-encoder","title":"Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages","date":"2022-05-02","arxiv_id":"2205.01086","repositories_listed":1,"syntology":null},{"url":"/paper/libris2s-a-german-english-speech-to-speech","slug":"libris2s-a-german-english-speech-to-speech","title":"LibriS2S: A German-English Speech-to-Speech Translation Corpus","date":"2022-04-22","arxiv_id":"2204.10593","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/stemm-self-learning-with-speech-text-manifold","slug":"stemm-self-learning-with-speech-text-manifold","title":"STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation","date":"2022-03-20","arxiv_id":"2203.10426","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"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) · 0 unverified","sample_list":"/paper/stemm-self-learning-with-speech-text-manifold#ran","syntology_url":"https://syntology.ai/paper/2203.10426","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.10426"}},"official":{"repos":["ictnlp/stemm"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/spanish-and-english-phoneme-recognition-by","slug":"spanish-and-english-phoneme-recognition-by","title":"Spanish and English Phoneme Recognition by Training on Simulated Classroom Audio Recordings of Collaborative Learning Environments","date":"2022-02-21","arxiv_id":"2202.10536","repositories_listed":1,"syntology":null},{"url":"/paper/cvss-corpus-and-massively-multilingual-speech","slug":"cvss-corpus-and-massively-multilingual-speech","title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","date":"2022-01-11","arxiv_id":"2201.03713","repositories_listed":1,"syntology":null},{"url":"/paper/a-wearable-sensor-vest-for-social-humanoid","slug":"a-wearable-sensor-vest-for-social-humanoid","title":"A wearable sensor vest for social humanoid robots with GPGPU, IoT, and modular software architecture","date":"2022-01-06","arxiv_id":"2201.02192","repositories_listed":1,"syntology":null},{"url":"/paper/instaindoor-and-multi-modal-deep-learning-for","slug":"instaindoor-and-multi-modal-deep-learning-for","title":"InstaIndoor and Multi-modal Deep Learning for Indoor Scene Recognition","date":"2021-12-23","arxiv_id":"2112.12409","repositories_listed":1,"syntology":null},{"url":"/paper/regularizing-end-to-end-speech-translation","slug":"regularizing-end-to-end-speech-translation","title":"Regularizing End-to-End Speech Translation with Triangular Decomposition Agreement","date":"2021-12-21","arxiv_id":"2112.10991","repositories_listed":1,"syntology":null},{"url":"/paper/x-vector-based-voice-activity-detection-for-1","slug":"x-vector-based-voice-activity-detection-for-1","title":"X-Vector based voice activity detection for multi-genre broadcast speech-to-text","date":"2021-12-09","arxiv_id":"2112.05016","repositories_listed":1,"syntology":null},{"url":"/paper/cross-attention-augmented-transducer-networks","slug":"cross-attention-augmented-transducer-networks","title":"Cross Attention Augmented Transducer Networks for Simultaneous Translation","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/editts-score-based-editing-for-controllable","slug":"editts-score-based-editing-for-controllable","title":"EdiTTS: Score-based Editing for Controllable Text-to-Speech","date":"2021-10-06","arxiv_id":"2110.02584","repositories_listed":1,"syntology":null},{"url":"/paper/late-reverberation-suppression-using-u-nets","slug":"late-reverberation-suppression-using-u-nets","title":"Late reverberation suppression using U-nets","date":"2021-10-05","arxiv_id":"2110.02144","repositories_listed":1,"syntology":null}],"syntology_records":22,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"papers_where_code_ran":24,"papers_where_code_ran_first_page":"/task/speech-to-text/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-to-text/papers/2","json":"/task/speech-to-text/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/speech-to-text/papers/3","json":"/task/speech-to-text/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/speech-to-text/papers/4","json":"/task/speech-to-text/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/speech-to-text/papers/5","json":"/task/speech-to-text/papers/5.json","rows":3},{"order":"ran","page":1,"of":1,"url":"/task/speech-to-text/papers/ran/1","json":"/task/speech-to-text/papers/ran/1.json","rows":24}],"description_links":{"kept":0,"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":"588e6c404561f43900844f5bbd2cc5218957b8126ddcf519e5731c753a424ab5","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}