{"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/phoneme-recognition","name":"Phoneme Recognition","slug":"phoneme-recognition","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":104,"papers_with_code":27,"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/timit","name":"TIMIT","full_name":"TIMIT Acoustic-Phonetic Continuous Speech Corpus","num_papers_in_archive":31}],"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":2,"rows_per_page":100,"shown":100,"of":104,"of_with_code":27,"tagged_in_all":104,"counts":{"archive_papers_tagged":104,"with_a_code_link":27,"where_syntology_ran_a_sample":4,"not_listed_spam_title":0,"listed":104,"listed_where_code_ran":4,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":4,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":4,"listed_every_run_a_failure_of_syntologys_instrument":0,"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/wavenet-a-generative-model-for-raw-audio","slug":"wavenet-a-generative-model-for-raw-audio","title":"WaveNet: A Generative Model for Raw Audio","date":"2016-09-12","arxiv_id":"1609.03499","repositories_listed":62,"syntology":{"n":103,"n_ran":65,"n_constructed":23,"n_ran_checked":52,"n_instrument":13,"n_unverified":38,"n_honours":2,"n_violates":1,"n_no_contract":49,"n_pointer_only":25,"phrase":"65 ran (of which 23 constructed an object rather than computing a result; 52 with no instrument failure: 2 honoured, 1 violated, 49 with no contract checked; 13 where Syntology's instrument failed) · 38 unverified","sample_list":"/paper/wavenet-a-generative-model-for-raw-audio#ran","syntology_url":"https://syntology.ai/paper/1609.03499","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.03499"}},"official":null}},{"url":"/paper/attention-based-models-for-speech-recognition","slug":"attention-based-models-for-speech-recognition","title":"Attention-Based Models for Speech Recognition","date":"2015-06-24","arxiv_id":"1506.07503","repositories_listed":14,"syntology":null},{"url":"/paper/sequence-transduction-with-recurrent-neural","slug":"sequence-transduction-with-recurrent-neural","title":"Sequence Transduction with Recurrent Neural Networks","date":"2012-11-14","arxiv_id":"1211.3711","repositories_listed":7,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"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) · 1 unverified","sample_list":"/paper/sequence-transduction-with-recurrent-neural#ran","syntology_url":"https://syntology.ai/paper/1211.3711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1211.3711"}},"official":null}},{"url":"/paper/speech-recognition-with-deep-recurrent-neural","slug":"speech-recognition-with-deep-recurrent-neural","title":"Speech Recognition with Deep Recurrent Neural Networks","date":"2013-03-22","arxiv_id":"1303.5778","repositories_listed":5,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"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) · 2 unverified","sample_list":"/paper/speech-recognition-with-deep-recurrent-neural#ran","syntology_url":"https://syntology.ai/paper/1303.5778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1303.5778"}},"official":null}},{"url":"/paper/improving-mispronunciation-detection-with","slug":"improving-mispronunciation-detection-with","title":"Improving Mispronunciation Detection with Wav2vec2-based Momentum Pseudo-Labeling for Accentedness and Intelligibility Assessment","date":"2022-03-29","arxiv_id":"2203.15937","repositories_listed":2,"syntology":null},{"url":"/paper/simple-and-effective-zero-shot-cross-lingual","slug":"simple-and-effective-zero-shot-cross-lingual","title":"Simple and Effective Zero-shot Cross-lingual Phoneme Recognition","date":"2021-09-23","arxiv_id":"2109.11680","repositories_listed":2,"syntology":null},{"url":"/paper/do-deep-nets-really-need-to-be-deep","slug":"do-deep-nets-really-need-to-be-deep","title":"Do Deep Nets Really Need to be Deep?","date":"2013-12-21","arxiv_id":"1312.6184","repositories_listed":2,"syntology":null},{"url":"/paper/laser-learning-by-aligning-self-supervised","slug":"laser-learning-by-aligning-self-supervised","title":"LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks","date":"2024-06-13","arxiv_id":"2406.09153","repositories_listed":1,"syntology":null},{"url":"/paper/score-self-supervised-correspondence-fine","slug":"score-self-supervised-correspondence-fine","title":"SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations","date":"2024-03-10","arxiv_id":"2403.06260","repositories_listed":1,"syntology":null},{"url":"/paper/fine-tuning-self-supervised-learning-models","slug":"fine-tuning-self-supervised-learning-models","title":"Fine-Tuning Self-Supervised Learning Models for End-to-End Pronunciation Scoring","date":"2023-09-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/allophant-cross-lingual-phoneme-recognition","slug":"allophant-cross-lingual-phoneme-recognition","title":"Allophant: Cross-lingual Phoneme Recognition with Articulatory Attributes","date":"2023-06-07","arxiv_id":"2306.04306","repositories_listed":1,"syntology":null},{"url":"/paper/mlphon-a-multifunctional-grapheme-phoneme","slug":"mlphon-a-multifunctional-grapheme-phoneme","title":"Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers","date":"2022-09-05","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fithubert-going-thinner-and-deeper-for","slug":"fithubert-going-thinner-and-deeper-for","title":"FitHuBERT: Going Thinner and Deeper for Knowledge Distillation of Speech Self-Supervised Learning","date":"2022-07-01","arxiv_id":"2207.00555","repositories_listed":1,"syntology":{"n":3,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"0 ran · 3 unverified","sample_list":"/paper/fithubert-going-thinner-and-deeper-for#ran","syntology_url":"https://syntology.ai/paper/2207.00555","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.00555"}},"official":{"repos":["glory20h/FitHuBERT"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":3,"ran_from_kinds":[]}}},{"url":"/paper/predicting-within-and-across-language-phoneme","slug":"predicting-within-and-across-language-phoneme","title":"Predicting within and across language phoneme recognition performance of self-supervised learning speech pre-trained models","date":"2022-06-24","arxiv_id":"2206.12489","repositories_listed":1,"syntology":null},{"url":"/paper/text-aware-end-to-end-mispronunciation","slug":"text-aware-end-to-end-mispronunciation","title":"Text-Aware End-to-end Mispronunciation Detection and Diagnosis","date":"2022-06-15","arxiv_id":"2206.07289","repositories_listed":1,"syntology":null},{"url":"/paper/deep-neural-convolutive-matrix-factorization","slug":"deep-neural-convolutive-matrix-factorization","title":"Deep Neural Convolutive Matrix Factorization for Articulatory Representation Decomposition","date":"2022-04-01","arxiv_id":"2204.00465","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-generative-latent-variable","slug":"benchmarking-generative-latent-variable","title":"Benchmarking Generative Latent Variable Models for Speech","date":"2022-02-22","arxiv_id":"2202.12707","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/benchmarking-generative-latent-variable#ran","syntology_url":"https://syntology.ai/paper/2202.12707","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.12707"}},"official":{"repos":["jakobhavtorn/benchmarking-lvms"],"state":"official (archive's flag): 3 ran","n_ran":3,"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/self-supervised-semantic-driven-phoneme","slug":"self-supervised-semantic-driven-phoneme","title":"Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition","date":"2021-11-16","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/singing-language-identification-using-a-deep","slug":"singing-language-identification-using-a-deep","title":"Singing Language Identification using a Deep Phonotactic Approach","date":"2021-05-31","arxiv_id":"2105.15014","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-low-resource-phoneme-recognition-on","slug":"real-time-low-resource-phoneme-recognition-on","title":"Real-time low-resource phoneme recognition on edge devices","date":"2021-03-25","arxiv_id":"2103.13997","repositories_listed":1,"syntology":null},{"url":"/paper/word-error-rate-estimation-without-asr-output","slug":"word-error-rate-estimation-without-asr-output","title":"Word Error Rate Estimation Without ASR Output: e-WER2","date":"2020-08-08","arxiv_id":"2008.03403","repositories_listed":1,"syntology":null},{"url":"/paper/application-of-word2vec-in-phoneme","slug":"application-of-word2vec-in-phoneme","title":"Application of Word2vec in Phoneme Recognition","date":"2019-12-17","arxiv_id":"1912.08011","repositories_listed":1,"syntology":null},{"url":"/paper/quaternion-convolutional-neural-networks-for-1","slug":"quaternion-convolutional-neural-networks-for-1","title":"Quaternion Convolutional Neural Networks for End-to-End Automatic Speech Recognition","date":"2018-06-20","arxiv_id":"1806.07789","repositories_listed":1,"syntology":null},{"url":"/paper/towards-end-to-end-speech-recognition-with","slug":"towards-end-to-end-speech-recognition-with","title":"Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks","date":"2017-01-10","arxiv_id":"1701.02720","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/towards-end-to-end-speech-recognition-with#ran","syntology_url":"https://syntology.ai/paper/1701.02720","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1701.02720"}},"official":null}},{"url":"/paper/regularizing-rnns-by-stabilizing-activations","slug":"regularizing-rnns-by-stabilizing-activations","title":"Regularizing RNNs by Stabilizing Activations","date":"2015-11-26","arxiv_id":"1511.08400","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-phoneme-sequence-recognition-using","slug":"end-to-end-phoneme-sequence-recognition-using","title":"End-to-end Phoneme Sequence Recognition using Convolutional Neural Networks","date":"2013-12-07","arxiv_id":"1312.2137","repositories_listed":1,"syntology":null},{"url":null,"slug":"using-neurogram-similarity-index-measure-nsim","title":"Using Neurogram Similarity Index Measure (NSIM) to Model Hearing Loss and Cochlear Neural Degeneration","date":"2025-06-15","arxiv_id":"2506.12705","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-to-text-translation-with-phoneme","title":"Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios","date":"2025-05-30","arxiv_id":"2505.24691","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-disentangling-the-contributions-of","title":"Towards disentangling the contributions of articulation and acoustics in multimodal phoneme recognition","date":"2025-05-29","arxiv_id":"2505.24059","repositories_listed":0,"syntology":null},{"url":null,"slug":"topological-deep-learning-for-speech-data","title":"Topological Deep Learning for Speech Data","date":"2025-05-27","arxiv_id":"2505.21173","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-models-for-phoneme","title":"Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning","date":"2025-03-06","arxiv_id":"2503.04710","repositories_listed":0,"syntology":null},{"url":null,"slug":"syntheticpop-attacking-speaker-verification","title":"SyntheticPop: Attacking Speaker Verification Systems With Synthetic VoicePops","date":"2025-02-13","arxiv_id":"2502.09553","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-cross-lingual-phonetic","title":"Improving Cross-Lingual Phonetic Representation of Low-Resource Languages Through Language Similarity Analysis","date":"2025-01-12","arxiv_id":"2501.06810","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-joint-spectro-temporal-relational-thinking","title":"A Joint Spectro-Temporal Relational Thinking Based Acoustic Modeling Framework","date":"2024-09-17","arxiv_id":"2409.15357","repositories_listed":0,"syntology":null},{"url":null,"slug":"slick-exploiting-subsequences-for-length","title":"SLiCK: Exploiting Subsequences for Length-Constrained Keyword Spotting","date":"2024-09-06","arxiv_id":"2409.09067","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepspeech-models-show-human-like-performance","title":"DeepSpeech models show Human-like Performance and Processing of Cochlear Implant Inputs","date":"2024-07-30","arxiv_id":"2407.20535","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-adapter-based-unified-model-for-multiple","title":"An Adapter-Based Unified Model for Multiple Spoken Language Processing Tasks","date":"2024-06-20","arxiv_id":"2406.14747","repositories_listed":0,"syntology":null},{"url":null,"slug":"tipaa-ssl-text-independent-phone-to-audio","title":"TIPAA-SSL: Text Independent Phone-to-Audio Alignment based on Self-Supervised Learning and Knowledge Transfer","date":"2024-05-03","arxiv_id":"2405.02124","repositories_listed":0,"syntology":null},{"url":null,"slug":"more-than-words-advancements-and-challenges","title":"More than words: Advancements and challenges in speech recognition for singing","date":"2024-03-14","arxiv_id":"2403.09298","repositories_listed":0,"syntology":null},{"url":null,"slug":"probing-the-information-encoded-in-neural","title":"Probing the Information Encoded in Neural-based Acoustic Models of Automatic Speech Recognition Systems","date":"2024-02-29","arxiv_id":"2402.19443","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-self-supervised-speech-models-on","title":"Analysis of Self-Supervised Speech Models on Children's Speech and Infant Vocalizations","date":"2024-02-10","arxiv_id":"2402.06888","repositories_listed":0,"syntology":null},{"url":null,"slug":"segment-boundary-detection-via-class-entropy","title":"Segment Boundary Detection via Class Entropy Measurements in Connectionist Phoneme Recognition","date":"2024-01-11","arxiv_id":"2401.05717","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-two-pass-cross-lingual-transfer","title":"Optimizing Two-Pass Cross-Lingual Transfer Learning: Phoneme Recognition and Phoneme to Grapheme Translation","date":"2023-12-06","arxiv_id":"2312.03312","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-of-speech-dependent-own-voice","title":"Modeling of Speech-dependent Own Voice Transfer Characteristics for Hearables with In-ear Microphones","date":"2023-10-10","arxiv_id":"2310.06554","repositories_listed":0,"syntology":null},{"url":null,"slug":"reduce-reuse-recycle-is-perturbed-data-better","title":"Reduce, Reuse, Recycle: Is Perturbed Data better than Other Language augmentation for Low Resource Self-Supervised Speech Models","date":"2023-09-22","arxiv_id":"2309.12763","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-end-to-end-multilingual-phoneme","title":"Boosting End-to-End Multilingual Phoneme Recognition through Exploiting Universal Speech Attributes Constraints","date":"2023-09-16","arxiv_id":"2309.08828","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-dependent-modeling-of-own-voice","title":"Speech-dependent Modeling of Own Voice Transfer Characteristics for In-ear Microphones in Hearables","date":"2023-09-15","arxiv_id":"2309.08294","repositories_listed":0,"syntology":null},{"url":null,"slug":"l1-aware-multilingual-mispronunciation","title":"L1-aware Multilingual Mispronunciation Detection Framework","date":"2023-09-14","arxiv_id":"2309.07719","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-child-vocalization-classification","title":"Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis","date":"2023-09-13","arxiv_id":"2309.07287","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-trust-explainable-ai-methods-on-asr-an","title":"Can We Trust Explainable AI Methods on ASR? An Evaluation on Phoneme Recognition","date":"2023-05-29","arxiv_id":"2305.18011","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-speech-data-augmentation","title":"A Comparison of Speech Data Augmentation Methods Using S3PRL Toolkit","date":"2023-02-27","arxiv_id":"2303.00510","repositories_listed":0,"syntology":null},{"url":null,"slug":"ensemble-knowledge-distillation-of-self","title":"Ensemble knowledge distillation of self-supervised speech models","date":"2023-02-24","arxiv_id":"2302.12757","repositories_listed":0,"syntology":null},{"url":null,"slug":"german-phoneme-recognition-with-text-to","title":"German Phoneme Recognition with Text-to-Phoneme Data Augmentation","date":"2022-11-24","arxiv_id":"2211.13776","repositories_listed":0,"syntology":null},{"url":null,"slug":"san-a-robust-end-to-end-asr-model","title":"SAN: a robust end-to-end ASR model architecture","date":"2022-10-27","arxiv_id":"2210.15285","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-zero-resource-speech-recognition","title":"Multilingual Zero Resource Speech Recognition Base on Self-Supervise Pre-Trained Acoustic Models","date":"2022-10-13","arxiv_id":"2210.06936","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-transformer-convolutional-and","title":"A Comparison of Transformer, Convolutional, and Recurrent Neural Networks on Phoneme Recognition","date":"2022-10-01","arxiv_id":"2210.00367","repositories_listed":0,"syntology":null},{"url":null,"slug":"speecheq-speech-emotion-recognition-based-on","title":"SpeechEQ: Speech Emotion Recognition based on Multi-scale Unified Datasets and Multitask Learning","date":"2022-06-27","arxiv_id":"2206.13101","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-data-augmentation-for-improving","title":"Speech Data Augmentation for Improving Phoneme Transcriptions of Aphasic Speech Using Wav2Vec 2.0 for the PSST Challenge","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"phoneme-transcription-of-endangered-languages","title":"Phoneme transcription of endangered languages: an evaluation of recent ASR architectures in the single speaker scenario","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-semantic-driven-phoneme-1","title":"Self-supervised Semantic-driven Phoneme Discovery for Zero-resource Speech Recognition","date":"2022-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"strata-word-boundaries-phoneme-recognition","title":"STRATA: Word Boundaries & Phoneme Recognition From Continuous Urdu Speech using Transfer Learning, Attention, & Data Augmentation","date":"2022-04-16","arxiv_id":"2204.07848","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-paradigm-for-articulatory-speech","title":"A Deep Paradigm for Articulatory Speech Representation Learning via Neural Convolutive Sparse Matrix Factorization","date":"2022-01-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"the-effectiveness-of-time-stretching-for","title":"The Effectiveness of Time Stretching for Enhancing Dysarthric Speech for Improved Dysarthric Speech Recognition","date":"2022-01-13","arxiv_id":"2201.04908","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-end-to-end-capt-system-for-l2","title":"A Novel End-to-End CAPT System for L2 Children Learners","date":"2021-11-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"a-dual-decoder-conformer-for-multilingual","title":"A Dual-Decoder Conformer for Multilingual Speech Recognition","date":"2021-08-22","arxiv_id":"2109.03277","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-speech-recognition-for-low","title":"Multilingual Speech Recognition for Low-Resource Indian Languages using Multi-Task conformer","date":"2021-08-22","arxiv_id":"2109.03969","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-recognition-of-suprasegmentals-in","title":"Automatic recognition of suprasegmentals in speech","date":"2021-08-02","arxiv_id":"2108.01122","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-with-cross-attention-for","title":"Multi-task Learning with Cross Attention for Keyword Spotting","date":"2021-07-15","arxiv_id":"2107.07634","repositories_listed":0,"syntology":null},{"url":null,"slug":"spoken-term-detection-methods-for-sparse","title":"Spoken Term Detection Methods for Sparse Transcription in Very Low-resource Settings","date":"2021-06-11","arxiv_id":"2106.06160","repositories_listed":0,"syntology":null},{"url":null,"slug":"phoneme-recognition-through-fine-tuning-of","title":"Phoneme Recognition through Fine Tuning of Phonetic Representations: a Case Study on Luhya Language Varieties","date":"2021-04-04","arxiv_id":"2104.01624","repositories_listed":0,"syntology":null},{"url":null,"slug":"mispronunciation-detection-in-non-native-l2","title":"Mispronunciation Detection in Non-native (L2) English with Uncertainty Modeling","date":"2021-01-16","arxiv_id":"2101.06396","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-discrete-latent-variable","title":"A Comparison of Discrete Latent Variable Models for Speech Representation Learning","date":"2020-10-24","arxiv_id":"2010.14230","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonlinear-isa-with-auxiliary-variables-for","title":"Nonlinear ISA with Auxiliary Variables for Learning Speech Representations","date":"2020-07-25","arxiv_id":"2007.12948","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-transcription-challenges-for-resource","title":"Speech Transcription Challenges for Resource Constrained Indigenous Language Cree","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-building-an-automatic-transcription","title":"Towards Building an Automatic Transcription System for Language Documentation: Experiences from Muyu","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-frequency-discrimination-and-phoneme","title":"Fast frequency discrimination and phoneme recognition using a biomimetic membrane coupled to a neural network","date":"2020-04-09","arxiv_id":"2004.04459","repositories_listed":0,"syntology":null},{"url":null,"slug":"detecting-mismatch-between-text-script-and","title":"Detecting Mismatch between Text Script and Voice-over Using Utterance Verification Based on Phoneme Recognition Ranking","date":"2020-03-20","arxiv_id":"2003.09180","repositories_listed":0,"syntology":null},{"url":null,"slug":"re-synchronization-using-the-hand-preceding","title":"Re-synchronization using the Hand Preceding Model for Multi-modal Fusion in Automatic Continuous Cued Speech Recognition","date":"2020-02-23","arxiv_id":"2001.00854","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-unsupervised-speech-recognition-and","title":"Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning","date":"2019-10-28","arxiv_id":"1910.12729","repositories_listed":0,"syntology":null},{"url":null,"slug":"taco-vc-a-single-speaker-tacotron-based-voice","title":"Taco-VC: A Single Speaker Tacotron based Voice Conversion with Limited Data","date":"2019-04-06","arxiv_id":"1904.03522","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speech-recognition-via-segmental","title":"Unsupervised Speech Recognition via Segmental Empirical Output Distribution Matching","date":"2018-12-23","arxiv_id":"1812.09323","repositories_listed":0,"syntology":null},{"url":null,"slug":"persian-vowel-recognition-with-mfcc-and-ann","title":"Persian Vowel recognition with MFCC and ANN on PCVC speech dataset","date":"2018-12-17","arxiv_id":"1812.06953","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-relevance-of-text-and-speech-features-in","title":"The Relevance of Text and Speech Features in Automatic Non-native English Accent Identification","date":"2018-04-16","arxiv_id":"1804.05689","repositories_listed":0,"syntology":null},{"url":null,"slug":"completely-unsupervised-phoneme-recognition","title":"Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings","date":"2018-04-01","arxiv_id":"1804.00316","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-aware-design-of-a-deep-convolutional","title":"Resource aware design of a deep convolutional-recurrent neural network for speech recognition through audio-visual sensor fusion","date":"2018-03-13","arxiv_id":"1803.04840","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-triphone-embedding-improves-phoneme","title":"Deep Triphone Embedding Improves Phoneme Recognition","date":"2017-10-22","arxiv_id":"1710.07868","repositories_listed":0,"syntology":null},{"url":null,"slug":"finding-phonemes-improving-machine-lip","title":"Finding phonemes: improving machine lip-reading","date":"2017-10-03","arxiv_id":"1710.01142","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-phoneme-recognition-with","title":"Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks","date":"2017-06-07","arxiv_id":"1706.02124","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-hard-alignments-with-variational","title":"Learning Hard Alignments with Variational Inference","date":"2017-05-16","arxiv_id":"1705.05524","repositories_listed":0,"syntology":null},{"url":null,"slug":"multitask-learning-with-low-level-auxiliary","title":"Multitask Learning with Low-Level Auxiliary Tasks for Encoder-Decoder Based Speech Recognition","date":"2017-04-05","arxiv_id":"1704.01631","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comprehensive-survey-on-bengali-phoneme","title":"A Comprehensive Survey on Bengali Phoneme Recognition","date":"2017-01-27","arxiv_id":"1701.08156","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimising-the-input-window-alignment-in-cd","title":"Optimising The Input Window Alignment in CD-DNN Based Phoneme Recognition for Low Latency Processing","date":"2016-06-29","arxiv_id":"1606.09163","repositories_listed":0,"syntology":null},{"url":null,"slug":"fpga-based-implementation-of-deep-neural","title":"FPGA Based Implementation of Deep Neural Networks Using On-chip Memory Only","date":"2016-02-04","arxiv_id":"1602.01616","repositories_listed":0,"syntology":null},{"url":null,"slug":"fixed-point-performance-analysis-of-recurrent","title":"Fixed-Point Performance Analysis of Recurrent Neural Networks","date":"2015-12-04","arxiv_id":"1512.01322","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-sequence-training-of-recurrent-neural","title":"Online Sequence Training of Recurrent Neural Networks with Connectionist Temporal Classification","date":"2015-11-21","arxiv_id":"1511.06841","repositories_listed":0,"syntology":null},{"url":null,"slug":"study-of-phonemes-confusions-in-hierarchical","title":"Study of Phonemes Confusions in Hierarchical Automatic Phoneme Recognition System","date":"2015-08-07","arxiv_id":"1508.01718","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-belief-function-in-svm-for","title":"Incorporating Belief Function in SVM for Phoneme Recognition","date":"2015-07-22","arxiv_id":"1507.06025","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-challenges-of-svm-optimization-using","title":"The challenges of SVM optimization using Adaboost on a phoneme recognition problem","date":"2015-07-22","arxiv_id":"1507.06028","repositories_listed":0,"syntology":null},{"url":null,"slug":"online-handwritten-devanagari-stroke","title":"Online Handwritten Devanagari Stroke Recognition Using Extended Directional Features","date":"2015-01-11","arxiv_id":"1501.02887","repositories_listed":0,"syntology":null}],"syntology_records":6,"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":4,"papers_where_code_ran_first_page":"/task/phoneme-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":2,"url":"/task/phoneme-recognition/papers/2","json":"/task/phoneme-recognition/papers/2.json","rows":4},{"order":"ran","page":1,"of":1,"url":"/task/phoneme-recognition/papers/ran/1","json":"/task/phoneme-recognition/papers/ran/1.json","rows":4}],"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":"b8796cf5b9af53c90cb3c8abaaf996da25448db2606715947f1b6096cc2be81f","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}