{"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/spoken-language-identification","name":"Spoken language identification","slug":"spoken-language-identification","description_markdown":"Identify the language being spoken from an audio input only.","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":51,"papers_with_code":13,"benchmarks":12,"benchmark_tables_in_archive":12,"benchmark_tables_shown":12,"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":4,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/spoken-language-identification-on-lre07","slug":"spoken-language-identification-on-lre07","dataset":"LRE07","dataset_url":null,"rows_in_archive":9,"metrics":["3 sec","10 sec","30 sec","Average"],"first_row_in_archive_order":{"model":"CNN-LDE","paper_title":"VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION","paper_url":"/paper/voxlingua107-a-dataset-for-spoken-language","paper_date":"2020-11-25","arxiv_id":"2011.12998","code_links":[],"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/voxlingua107-a-dataset-for-spoken-language#ran","syntology_url":"https://syntology.ai/paper/2011.12998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12998"}},"official":null}}},{"leaderboard":"/sota/spoken-language-identification-on-voxforge-1","slug":"spoken-language-identification-on-voxforge-1","dataset":"VoxForge European","dataset_url":"/dataset/voxforge","rows_in_archive":5,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"2D ConvNet(MixUp=YES)","paper_title":"Spoken Language Identification using ConvNets","paper_url":"/paper/spoken-language-identification-using-convnets","paper_date":"2019-10-09","arxiv_id":"1910.04269","code_links":[],"syntology":null}},{"leaderboard":"/sota/spoken-language-identification-on-youtube","slug":"spoken-language-identification-on-youtube","dataset":"YouTube News dataset (No Noise)","dataset_url":null,"rows_in_archive":5,"metrics":["Accuracy ","F1 Score"],"first_row_in_archive_order":{"model":"CRNN","paper_title":"Is Attention always needed? A Case Study on Language Identification from Speech","paper_url":"/paper/is-attention-always-needed-a-case-study-on","paper_date":"2021-10-05","arxiv_id":"2110.03427","code_links":[],"syntology":null}},{"leaderboard":"/sota/spoken-language-identification-on-youtube-1","slug":"spoken-language-identification-on-youtube-1","dataset":"YouTube News dataset (White Noise)","dataset_url":null,"rows_in_archive":5,"metrics":["Accuracy ","F1 Score"],"first_row_in_archive_order":{"model":"CRNN","paper_title":"Is Attention always needed? A Case Study on Language Identification from Speech","paper_url":"/paper/is-attention-always-needed-a-case-study-on","paper_date":"2021-10-05","arxiv_id":"2110.03427","code_links":[],"syntology":null}},{"leaderboard":"/sota/spoken-language-identification-on-1","slug":"spoken-language-identification-on-1","dataset":"Untranscribed mixed-speech dataset","dataset_url":null,"rows_in_archive":4,"metrics":["ACC","PRC","RCL"],"first_row_in_archive_order":{"model":"SVM","paper_title":"Automatic Dialect Detection in Arabic Broadcast Speech","paper_url":"/paper/automatic-dialect-detection-in-arabic","paper_date":"2015-09-23","arxiv_id":"1509.06928","code_links":[{"title":"Qatar-Computing-Research-Institute/dialectID","url":"https://github.com/Qatar-Computing-Research-Institute/dialectID"}],"syntology":null}},{"leaderboard":"/sota/spoken-language-identification-on-voxforge","slug":"spoken-language-identification-on-voxforge","dataset":"VoxForge Commonwealth","dataset_url":"/dataset/voxforge","rows_in_archive":4,"metrics":["Accuracy (%)"],"first_row_in_archive_order":{"model":"2D ConvNet(MixUp=YES)","paper_title":"Spoken Language Identification using ConvNets","paper_url":"/paper/spoken-language-identification-using-convnets","paper_date":"2019-10-09","arxiv_id":"1910.04269","code_links":[],"syntology":null}},{"leaderboard":"/sota/spoken-language-identification-on-indictts","slug":"spoken-language-identification-on-indictts","dataset":"IndicTTS","dataset_url":"/dataset/indictts","rows_in_archive":3,"metrics":["Classification Accuracy"],"first_row_in_archive_order":{"model":"CRNN","paper_title":"Is Attention always needed? A Case Study on Language Identification from Speech","paper_url":"/paper/is-attention-always-needed-a-case-study-on","paper_date":"2021-10-05","arxiv_id":"2110.03427","code_links":[],"syntology":null}},{"leaderboard":"/sota/spoken-language-identification-on-voxforge-2","slug":"spoken-language-identification-on-voxforge-2","dataset":"VoxForge","dataset_url":"/dataset/voxforge","rows_in_archive":3,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"LEAF","paper_title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","paper_url":"/paper/efficientleaf-a-faster-learnable-audio","paper_date":"2022-07-12","arxiv_id":"2207.05508","code_links":[{"title":"cpjku/efficientleaf","url":"https://github.com/cpjku/efficientleaf"}],"syntology":null}},{"leaderboard":"/sota/spoken-language-identification-on","slug":"spoken-language-identification-on","dataset":"VOXLINGUA107","dataset_url":"/dataset/voxlingua107","rows_in_archive":2,"metrics":["0..5sec","5..20sec","Average"],"first_row_in_archive_order":{"model":"Noisy","paper_title":"VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION","paper_url":"/paper/voxlingua107-a-dataset-for-spoken-language","paper_date":"2020-11-25","arxiv_id":"2011.12998","code_links":[],"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/voxlingua107-a-dataset-for-spoken-language#ran","syntology_url":"https://syntology.ai/paper/2011.12998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12998"}},"official":null}}},{"leaderboard":"/sota/spoken-language-identification-on-kalaka-3","slug":"spoken-language-identification-on-kalaka-3","dataset":"KALAKA-3","dataset_url":null,"rows_in_archive":2,"metrics":["PC","EC","EO","PO"],"first_row_in_archive_order":{"model":"Model on the automatically filtered (cleaned) data","paper_title":"VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION","paper_url":"/paper/voxlingua107-a-dataset-for-spoken-language","paper_date":"2020-11-25","arxiv_id":"2011.12998","code_links":[],"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/voxlingua107-a-dataset-for-spoken-language#ran","syntology_url":"https://syntology.ai/paper/2011.12998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12998"}},"official":null}}},{"leaderboard":"/sota/spoken-language-identification-on-youtube-2","slug":"spoken-language-identification-on-youtube-2","dataset":"YouTube News dataset (Crackling Noise)","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy ","F1 Score"],"first_row_in_archive_order":{"model":"Inception-v3 CRNN","paper_title":"Language Identification Using Deep Convolutional Recurrent Neural Networks","paper_url":"/paper/language-identification-using-deep","paper_date":"2017-08-16","arxiv_id":"1708.04811","code_links":[{"title":"HPI-DeepLearning/crnn-lid","url":"https://github.com/HPI-DeepLearning/crnn-lid"}],"syntology":null}},{"leaderboard":"/sota/spoken-language-identification-on-youtube-3","slug":"spoken-language-identification-on-youtube-3","dataset":"YouTube News dataset (Background Music)","dataset_url":null,"rows_in_archive":2,"metrics":["Accuracy ","F1 Score"],"first_row_in_archive_order":{"model":"Inception-v3 CRNN","paper_title":"Language Identification Using Deep Convolutional Recurrent Neural Networks","paper_url":"/paper/language-identification-using-deep","paper_date":"2017-08-16","arxiv_id":"1708.04811","code_links":[{"title":"HPI-DeepLearning/crnn-lid","url":"https://github.com/HPI-DeepLearning/crnn-lid"}],"syntology":null}}],"datasets":[{"url":"/dataset/fleurs","name":"FLEURS","full_name":"Few-shot Learning Evaluation of Universal Representations of Speech","num_papers_in_archive":141},{"url":"/dataset/voxforge","name":"VoxForge","full_name":"VoxForge","num_papers_in_archive":11},{"url":"/dataset/indictts","name":"IndicTTS","full_name":"","num_papers_in_archive":3},{"url":"/dataset/voxlingua107","name":"VOXLINGUA107","full_name":"","num_papers_in_archive":2}],"subtasks":[],"parent_tasks":[{"url":"/task/spoken-language-understanding","name":"Spoken Language Understanding"}],"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":1,"rows_per_page":100,"shown":51,"of":51,"of_with_code":13,"tagged_in_all":51,"counts":{"archive_papers_tagged":51,"with_a_code_link":13,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":51,"listed_where_code_ran":1,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":1,"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/voxlingua107-a-dataset-for-spoken-language-1","slug":"voxlingua107-a-dataset-for-spoken-language-1","title":"VoxLingua107: a Dataset for Spoken Language Recognition","date":"2020-11-25","arxiv_id":"2011.12998","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/voxlingua107-a-dataset-for-spoken-language-1#ran","syntology_url":"https://syntology.ai/paper/2011.12998","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.12998"}},"official":{"repos":["alumae/torch-xvectors-wav"],"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/afrihubert-a-self-supervised-speech","slug":"afrihubert-a-self-supervised-speech","title":"AfriHuBERT: A self-supervised speech representation model for African languages","date":"2024-09-30","arxiv_id":"2409.20201","repositories_listed":1,"syntology":null},{"url":"/paper/improving-multilingual-asr-in-the-wild-using","slug":"improving-multilingual-asr-in-the-wild-using","title":"Improving Multilingual ASR in the Wild Using Simple N-best Re-ranking","date":"2024-09-27","arxiv_id":"2409.18428","repositories_listed":1,"syntology":null},{"url":"/paper/towards-training-bilingual-and-code-switched","slug":"towards-training-bilingual-and-code-switched","title":"Unified model for code-switching speech recognition and language identification based on a concatenated tokenizer","date":"2023-06-14","arxiv_id":"2306.08753","repositories_listed":1,"syntology":null},{"url":"/paper/spoken-language-identification-system-for","slug":"spoken-language-identification-system-for","title":"Spoken Language Identification System for English-Mandarin Code-Switching Child-Directed Speech","date":"2023-06-01","arxiv_id":"2306.00736","repositories_listed":1,"syntology":null},{"url":"/paper/improving-spoken-language-identification-with","slug":"improving-spoken-language-identification-with","title":"Improving Spoken Language Identification with Map-Mix","date":"2023-02-16","arxiv_id":"2302.08229","repositories_listed":1,"syntology":null},{"url":"/paper/distilled-non-semantic-speech-embeddings-with","slug":"distilled-non-semantic-speech-embeddings-with","title":"Distilled Non-Semantic Speech Embeddings with Binary Neural Networks for Low-Resource Devices","date":"2022-07-12","arxiv_id":"2207.05784","repositories_listed":1,"syntology":null},{"url":"/paper/efficientleaf-a-faster-learnable-audio","slug":"efficientleaf-a-faster-learnable-audio","title":"EfficientLEAF: A Faster LEarnable Audio Frontend of Questionable Use","date":"2022-07-12","arxiv_id":"2207.05508","repositories_listed":1,"syntology":null},{"url":"/paper/bert-lid-leveraging-bert-to-improve-spoken","slug":"bert-lid-leveraging-bert-to-improve-spoken","title":"BERT-LID: Leveraging BERT to Improve Spoken Language Identification","date":"2022-03-01","arxiv_id":"2203.00328","repositories_listed":1,"syntology":null},{"url":"/paper/triplet-entropy-loss-improving-the","slug":"triplet-entropy-loss-improving-the","title":"Triplet Entropy Loss: Improving The Generalisation of Short Speech Language Identification Systems","date":"2020-12-03","arxiv_id":"2012.03775","repositories_listed":1,"syntology":null},{"url":"/paper/cross-domain-adaptation-of-spoken-language","slug":"cross-domain-adaptation-of-spoken-language","title":"Cross-Domain Adaptation of Spoken Language Identification for Related Languages: The Curious Case of Slavic Languages","date":"2020-08-02","arxiv_id":"2008.00545","repositories_listed":1,"syntology":null},{"url":"/paper/language-identification-using-deep","slug":"language-identification-using-deep","title":"Language Identification Using Deep Convolutional Recurrent Neural Networks","date":"2017-08-16","arxiv_id":"1708.04811","repositories_listed":1,"syntology":null},{"url":"/paper/automatic-dialect-detection-in-arabic","slug":"automatic-dialect-detection-in-arabic","title":"Automatic Dialect Detection in Arabic Broadcast Speech","date":"2015-09-23","arxiv_id":"1509.06928","repositories_listed":1,"syntology":null},{"url":null,"slug":"on-the-use-of-performer-and-agent-attention","title":"On the use of Performer and Agent Attention for Spoken Language Identification","date":"2025-02-09","arxiv_id":"2502.05841","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-spoken-language-identification","title":"Exploring Spoken Language Identification Strategies for Automatic Transcription of Multilingual Broadcast and Institutional Speech","date":"2024-06-13","arxiv_id":"2406.09290","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-linguistic-representation-for","title":"Generative linguistic representation for spoken language identification","date":"2023-12-18","arxiv_id":"2312.10964","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-adaptive-pre-training-of","title":"Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification","date":"2023-12-12","arxiv_id":"2312.07338","repositories_listed":0,"syntology":null},{"url":null,"slug":"wavelet-scattering-transform-for-improving","title":"Wavelet Scattering Transform for Improving Generalization in Low-Resourced Spoken Language Identification","date":"2023-10-01","arxiv_id":"2310.00602","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-modeling-for-spoken-language","title":"Multimodal Modeling For Spoken Language Identification","date":"2023-09-19","arxiv_id":"2309.10567","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-open-set-spoken-language","title":"Robust Open-Set Spoken Language Identification and the CU MultiLang Dataset","date":"2023-08-29","arxiv_id":"2308.14951","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-corpora-spoken-language-identification","title":"Cross-Corpora Spoken Language Identification with Domain Diversification and Generalization","date":"2023-02-10","arxiv_id":"2302.05110","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overview-of-indian-spoken-language","title":"An Overview of Indian Spoken Language Recognition from Machine Learning Perspective","date":"2022-11-30","arxiv_id":"2212.03812","repositories_listed":0,"syntology":null},{"url":null,"slug":"accidental-learners-spoken-language","title":"Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models","date":"2022-11-09","arxiv_id":"2211.05103","repositories_listed":0,"syntology":null},{"url":null,"slug":"ambernet-a-compact-end-to-end-model-for","title":"A Compact End-to-End Model with Local and Global Context for Spoken Language Identification","date":"2022-10-27","arxiv_id":"2210.15781","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-end-to-end-spoken","title":"Deep learning-based end-to-end spoken language identification system for domain-mismatched scenario","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-synthesis-based-data-augmentation","title":"Adversarial synthesis based data-augmentation for code-switched spoken language identification","date":"2022-05-30","arxiv_id":"2205.15747","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-spoken-language-identification-1","title":"Automatic Spoken Language Identification using a Time-Delay Neural Network","date":"2022-05-19","arxiv_id":"2205.09564","repositories_listed":0,"syntology":null},{"url":null,"slug":"pretraining-approaches-for-spoken-language","title":"Pretraining Approaches for Spoken Language Recognition: TalTech Submission to the OLR 2021 Challenge","date":"2022-05-14","arxiv_id":"2205.07083","repositories_listed":0,"syntology":null},{"url":null,"slug":"automated-speech-tools-for-helping","title":"Automated speech tools for helping communities process restricted-access corpora for language revival efforts","date":"2022-04-15","arxiv_id":"2204.07272","repositories_listed":0,"syntology":null},{"url":null,"slug":"transducer-based-language-embedding-for","title":"Transducer-based language embedding for spoken language identification","date":"2022-04-08","arxiv_id":"2204.03888","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-language-identification-of-accented","title":"Improving Language Identification of Accented Speech","date":"2022-03-31","arxiv_id":"2203.16972","repositories_listed":0,"syntology":null},{"url":null,"slug":"partial-coupling-of-optimal-transport-for","title":"Partial Coupling of Optimal Transport for Spoken Language Identification","date":"2022-03-31","arxiv_id":"2203.17036","repositories_listed":0,"syntology":null},{"url":null,"slug":"mslam-massively-multilingual-joint-pre","title":"mSLAM: Massively multilingual joint pre-training for speech and text","date":"2022-02-03","arxiv_id":"2202.01374","repositories_listed":0,"syntology":null},{"url":"/paper/is-attention-always-needed-a-case-study-on","slug":"is-attention-always-needed-a-case-study-on","title":"Is Attention always needed? A Case Study on Language Identification from Speech","date":"2021-10-05","arxiv_id":"2110.03427","repositories_listed":0,"syntology":null},{"url":null,"slug":"sigtyp-2021-shared-task-robust-spoken","title":"SIGTYP 2021 Shared Task: Robust Spoken Language Identification","date":"2021-06-07","arxiv_id":"2106.03895","repositories_listed":0,"syntology":null},{"url":null,"slug":"anlirika-an-lstm-cnn-flow-twister-for-spoken","title":"Anlirika: An LSTM–CNN Flow Twister for Spoken Language Identification","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"language-id-prediction-from-speech-using-self-1","title":"Language ID Prediction from Speech Using Self-Attentive Pooling","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-spoken-language-identification","title":"Low-Resource Spoken Language Identification Using Self-Attentive Pooling and Deep 1D Time-Channel Separable Convolutions","date":"2021-05-31","arxiv_id":"2106.00052","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-corpora-language-recognition-a","title":"Cross-Corpora Language Recognition: A Preliminary Investigation with Indian Languages","date":"2021-05-10","arxiv_id":"2105.04639","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-id-prediction-from-speech-using-self","title":"Language ID Prediction from Speech Using Self-Attentive Pooling and 1D-Convolutions","date":"2021-04-24","arxiv_id":"2104.11985","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-neural-adaptation-model-based-on","title":"Unsupervised neural adaptation model based on optimal transport for spoken language identification","date":"2020-12-24","arxiv_id":"2012.13152","repositories_listed":0,"syntology":null},{"url":"/paper/voxlingua107-a-dataset-for-spoken-language","slug":"voxlingua107-a-dataset-for-spoken-language","title":"VOXLINGUA107: A DATASET FOR SPOKEN LANGUAGE RECOGNITION","date":"2020-11-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rediscovering-the-slavic-continuum-in","title":"Rediscovering the Slavic Continuum in Representations Emerging from Neural Models of Spoken Language Identification","date":"2020-10-22","arxiv_id":"2010.11973","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-spectral-augmentation-for-code","title":"Exploiting Spectral Augmentation for Code-Switched Spoken Language Identification","date":"2020-10-14","arxiv_id":"2010.07130","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-on-spoken-language-identification","title":"A Study on Spoken Language Identification using Deep Neural Networks","date":"2020-09-15","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-performance-of-time-pooling-strategies","title":"On The Performance of Time-Pooling Strategies for End-to-End Spoken Language Identification","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-language-identification-for","title":"Improving Language Identification for Multilingual Speakers","date":"2020-01-29","arxiv_id":"2001.11019","repositories_listed":0,"syntology":null},{"url":"/paper/spoken-language-identification-using-convnets","slug":"spoken-language-identification-using-convnets","title":"Spoken Language Identification using ConvNets","date":"2019-10-09","arxiv_id":"1910.04269","repositories_listed":0,"syntology":null},{"url":null,"slug":"methods-for-spoken-language-identification","title":"Methods for Spoken Language Identification","date":"2017-12-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"spoken-language-identification-with","title":"Spoken Language Identification with Phonotactics Methods on Minangkabau, Sundanese, and Javanese Languages","date":"2016-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-spoken-language-identification","title":"Automatic Spoken Language Identification Utilizing Acoustic and Phonetic Speech Information","date":"2004-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null}],"syntology_records":1,"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":1,"papers_where_code_ran_first_page":"/task/spoken-language-identification/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":"ran","page":1,"of":1,"url":"/task/spoken-language-identification/papers/ran/1","json":"/task/spoken-language-identification/papers/ran/1.json","rows":1}],"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":"1cd31db5a819358879454fdba9fe9c0d856ba3adcc765cd52de7aed24ab39865","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}