{"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/acoustic-modelling","name":"Acoustic Modelling","slug":"acoustic-modelling","description_markdown":null,"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":49,"papers_with_code":11,"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/salmon","name":"SALMon","full_name":"","num_papers_in_archive":9}],"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":1,"rows_per_page":100,"shown":49,"of":49,"of_with_code":11,"tagged_in_all":49,"counts":{"archive_papers_tagged":49,"with_a_code_link":11,"where_syntology_ran_a_sample":1,"not_listed_spam_title":0,"listed":49,"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/spear-receiver-to-receiver-acoustic-neural","slug":"spear-receiver-to-receiver-acoustic-neural","title":"SPEAR: Receiver-to-Receiver Acoustic Neural Warping Field","date":"2024-06-16","arxiv_id":"2406.11006","repositories_listed":1,"syntology":null},{"url":"/paper/sonotracelab-a-raytracing-based-acoustic","slug":"sonotracelab-a-raytracing-based-acoustic","title":"SonoTraceLab - A Raytracing-Based Acoustic Modelling System for Simulating Echolocation Behavior of Bats","date":"2024-03-11","arxiv_id":"2403.06847","repositories_listed":1,"syntology":null},{"url":"/paper/matcha-tts-a-fast-tts-architecture-with","slug":"matcha-tts-a-fast-tts-architecture-with","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","date":"2023-09-06","arxiv_id":"2309.03199","repositories_listed":1,"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":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) · 0 unverified","sample_list":"/paper/matcha-tts-a-fast-tts-architecture-with#ran","syntology_url":"https://syntology.ai/paper/2309.03199","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.03199"}},"official":{"repos":["shivammehta25/Matcha-TTS"],"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/common-phone-a-multilingual-dataset-for","slug":"common-phone-a-multilingual-dataset-for","title":"Common Phone: A Multilingual Dataset for Robust Acoustic Modelling","date":"2022-01-15","arxiv_id":"2201.05912","repositories_listed":1,"syntology":null},{"url":"/paper/multilingual-bottleneck-features-for","slug":"multilingual-bottleneck-features-for","title":"Multilingual Bottleneck Features for Improving ASR Performance of Code-Switched Speech in Under-Resourced Languages","date":"2020-10-31","arxiv_id":"2011.03118","repositories_listed":1,"syntology":null},{"url":"/paper/acoustic-model-adaptation-from-raw-waveforms","slug":"acoustic-model-adaptation-from-raw-waveforms","title":"Acoustic Model Adaptation from Raw Waveforms with SincNet","date":"2019-09-30","arxiv_id":"1909.13759","repositories_listed":1,"syntology":null},{"url":"/paper/gibbonr-an-r-package-for-the-detection-and","slug":"gibbonr-an-r-package-for-the-detection-and","title":"GIBBONFINDR: An R package for the detection and classification of acoustic signals","date":"2019-06-06","arxiv_id":"1906.02572","repositories_listed":1,"syntology":null},{"url":"/paper/wgansing","slug":"wgansing","title":"WGANSing","date":"2019-03-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/evaluation-phonemic-transcription-of-low","slug":"evaluation-phonemic-transcription-of-low","title":"Evaluation Phonemic Transcription of Low-Resource Tonal Languages for Language Documentation","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/phonemic-transcription-of-low-resource-tonal","slug":"phonemic-transcription-of-low-resource-tonal","title":"Phonemic Transcription of Low-Resource Tonal Languages","date":"2017-12-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-attention-based-large-vocabulary","slug":"end-to-end-attention-based-large-vocabulary","title":"End-to-End Attention-based Large Vocabulary Speech Recognition","date":"2015-08-18","arxiv_id":"1508.04395","repositories_listed":1,"syntology":null},{"url":null,"slug":"language-modelling-for-speaker-diarization-in","title":"Language Modelling for Speaker Diarization in Telephonic Interviews","date":"2025-01-28","arxiv_id":"2501.17893","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-overview-of-text-to-speech-systems-and","title":"An overview of text-to-speech systems and media applications","date":"2023-10-22","arxiv_id":"2310.14301","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparing-normalizing-flows-and-diffusion","title":"Comparing normalizing flows and diffusion models for prosody and acoustic modelling in text-to-speech","date":"2023-07-31","arxiv_id":"2307.16679","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-and-age-invariant-training-for-child","title":"Speaker- and Age-Invariant Training for Child Acoustic Modeling Using Adversarial Multi-Task Learning","date":"2022-10-19","arxiv_id":"2210.10231","repositories_listed":0,"syntology":null},{"url":null,"slug":"impact-of-dataset-on-acoustic-models-for","title":"Impact of Dataset on Acoustic Models for Automatic Speech Recognition","date":"2022-03-25","arxiv_id":"2203.13590","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-deep-neural-network-acoustic","title":"Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition","date":"2022-01-24","arxiv_id":"2201.09432","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-audio-quality-for-expressive-neural","title":"Enhancing audio quality for expressive Neural Text-to-Speech","date":"2021-08-13","arxiv_id":"2108.06270","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-resource-german-asr-with-untranscribed","title":"Low Resource German ASR with Untranscribed Data Spoken by Non-native Children -- INTERSPEECH 2021 Shared Task SPAPL System","date":"2021-06-18","arxiv_id":"2106.09963","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-acoustic-modelling-for-phone","title":"End-to-end acoustic modelling for phone recognition of young readers","date":"2021-03-04","arxiv_id":"2103.02899","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-study-of-two-dimensional-vocal","title":"A comparative study of two-dimensional vocal tract acoustic modeling based on Finite-Difference Time-Domain methods","date":"2021-02-09","arxiv_id":"2102.04588","repositories_listed":0,"syntology":null},{"url":null,"slug":"wadenet-wavelet-decomposition-based-cnn-for","title":"WaDeNet: Wavelet Decomposition based CNN for Speech Processing","date":"2020-11-11","arxiv_id":"2011.05594","repositories_listed":0,"syntology":null},{"url":null,"slug":"fully-convolutional-asr-for-less-resourced","title":"Fully Convolutional ASR for Less-Resourced Endangered Languages","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-modelling-for-five-1","title":"Semi-supervised Acoustic Modelling for Five-lingual Code-switched ASR using Automatically-segmented Soap Opera Speech","date":"2020-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-modelling-for-five","title":"Semi-supervised acoustic modelling for five-lingual code-switched ASR using automatically-segmented soap opera speech","date":"2020-04-08","arxiv_id":"2004.06480","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-lingual-transfer-learning-for-zero","title":"Cross lingual transfer learning for zero-resource domain adaptation","date":"2019-10-29","arxiv_id":"1910.02168","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-low-resource-somali-speech","title":"Improved low-resource Somali speech recognition by semi-supervised acoustic and language model training","date":"2019-07-06","arxiv_id":"1907.03064","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-span-acoustic-modelling-using-raw","title":"Multi-Span Acoustic Modelling using Raw Waveform Signals","date":"2019-06-21","arxiv_id":"1906.11047","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-acoustic-model-training-for-1","title":"Semi-supervised acoustic model training for five-lingual code-switched ASR","date":"2019-06-20","arxiv_id":"1906.08647","repositories_listed":0,"syntology":null},{"url":null,"slug":"cumulative-adaptation-for-blstm-acoustic","title":"Cumulative Adaptation for BLSTM Acoustic Models","date":"2019-06-14","arxiv_id":"1906.06207","repositories_listed":0,"syntology":null},{"url":null,"slug":"densely-connected-convolutional-networks-for","title":"Densely Connected Convolutional Networks for Speech Recognition","date":"2018-08-10","arxiv_id":"1808.03570","repositories_listed":0,"syntology":null},{"url":null,"slug":"lip-reading-driven-deep-learning-approach-for","title":"Lip-Reading Driven Deep Learning Approach for Speech Enhancement","date":"2018-07-31","arxiv_id":"1808.00046","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-encoder-decoder-models-for-unsupervised","title":"Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis","date":"2018-07-30","arxiv_id":"1807.11470","repositories_listed":0,"syntology":null},{"url":null,"slug":"forward-attention-in-sequence-to-sequence","title":"Forward Attention in Sequence-to-sequence Acoustic Modelling for Speech Synthesis","date":"2018-07-18","arxiv_id":"1807.06736","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-order-recurrent-neural-networks-for","title":"High Order Recurrent Neural Networks for Acoustic Modelling","date":"2018-02-22","arxiv_id":"1802.08314","repositories_listed":0,"syntology":null},{"url":null,"slug":"semi-supervised-learning-with-sparse","title":"Semi-supervised Learning with Sparse Autoencoders in Phone Classification","date":"2016-10-03","arxiv_id":"1610.00520","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-mgb-2-challenge-arabic-multi-dialect","title":"The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition","date":"2016-09-19","arxiv_id":"1609.05625","repositories_listed":0,"syntology":null},{"url":null,"slug":"knowledge-distillation-for-small-footprint","title":"Knowledge Distillation for Small-footprint Highway Networks","date":"2016-08-02","arxiv_id":"1608.00892","repositories_listed":0,"syntology":null},{"url":"/paper/segmental-recurrent-neural-networks-for-end","slug":"segmental-recurrent-neural-networks-for-end","title":"Segmental Recurrent Neural Networks for End-to-end Speech Recognition","date":"2016-03-01","arxiv_id":"1603.00223","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-2015-sheffield-system-for-transcription","title":"The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media","date":"2015-12-21","arxiv_id":"1512.06643","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-dirichlet-allocation-based","title":"Latent Dirichlet Allocation Based Organisation of Broadcast Media Archives for Deep Neural Network Adaptation","date":"2015-11-16","arxiv_id":"1511.05076","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-domain-discovery-using-latent","title":"Unsupervised Domain Discovery using Latent Dirichlet Allocation for Acoustic Modelling in Speech Recognition","date":"2015-09-08","arxiv_id":"1509.02412","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-adaptation-and-adaptive-training-for","title":"Model adaptation and adaptive training for the recognition of dysarthric speech","date":"2015-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hybridized-feature-extraction-and-acoustic","title":"Hybridized Feature Extraction and Acoustic Modelling Approach for Dysarthric Speech Recognition","date":"2015-06-06","arxiv_id":"1506.02170","repositories_listed":0,"syntology":null},{"url":"/paper/deep-recurrent-neural-networks-for-acoustic","slug":"deep-recurrent-neural-networks-for-acoustic","title":"Deep Recurrent Neural Networks for Acoustic Modelling","date":"2015-04-07","arxiv_id":"1504.01482","repositories_listed":0,"syntology":null},{"url":null,"slug":"free-on-line-speech-recogniser-based-on-kaldi","title":"Free on-line speech recogniser based on Kaldi ASR toolkit producing word posterior lattices","date":"2014-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-language-identification-using-deep","title":"AUTOMATIC LANGUAGE IDENTIFICATION USING DEEP NEURAL NETWORKS","date":"2014-05-04","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploiting-the-large-scale-german-broadcast","title":"Exploiting the large-scale German Broadcast Corpus to boost the Fraunhofer IAIS Speech Recognition System","date":"2014-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"hesitate-in-portuguese","title":"HESITA(te) in Portuguese","date":"2014-05-01","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/acoustic-modelling/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/acoustic-modelling/papers/ran/1","json":"/task/acoustic-modelling/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":"6510bcf8c72e239406abe6f2c0d778535bc45a7aa6c5943286e741c1e680eb50","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}