{"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/sequence-to-sequence-speech-recognition","name":"Sequence-To-Sequence Speech Recognition","slug":"sequence-to-sequence-speech-recognition","description_markdown":null,"categories":[{"name":"Audio","url":"/area/audio"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":22,"papers_with_code":7,"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":0,"subtasks":0,"parent_tasks":1},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/speech-recognition","name":"Speech Recognition"}],"papers":{"order":"repositories listed in the archive (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":1,"rows_per_page":100,"shown":22,"of":22,"of_with_code":7,"tagged_in_all":22,"counts":{"archive_papers_tagged":22,"with_a_code_link":7,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":22,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"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/model-unit-exploration-for-sequence-to","slug":"model-unit-exploration-for-sequence-to","title":"On the Choice of Modeling Unit for Sequence-to-Sequence Speech Recognition","date":"2019-02-05","arxiv_id":"1902.01955","repositories_listed":3,"syntology":null},{"url":"/paper/lingvo-a-modular-and-scalable-framework-for","slug":"lingvo-a-modular-and-scalable-framework-for","title":"Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling","date":"2019-02-21","arxiv_id":"1902.08295","repositories_listed":2,"syntology":{"n":4,"n_ran":4,"n_constructed":0,"n_ran_checked":4,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/lingvo-a-modular-and-scalable-framework-for#ran","syntology_url":"https://syntology.ai/paper/1902.08295","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1902.08295"}},"official":{"repos":["tensorflow/lingvo"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/instant-one-shot-word-learning-for-context","slug":"instant-one-shot-word-learning-for-context","title":"Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition","date":"2021-07-05","arxiv_id":"2107.02268","repositories_listed":1,"syntology":null},{"url":"/paper/low-latency-sequence-to-sequence-speech","slug":"low-latency-sequence-to-sequence-speech","title":"Low-Latency Sequence-to-Sequence Speech Recognition and Translation by Partial Hypothesis Selection","date":"2020-05-22","arxiv_id":"2005.11185","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":1,"n_violates":0,"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: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/low-latency-sequence-to-sequence-speech#ran","syntology_url":"https://syntology.ai/paper/2005.11185","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11185"}},"official":{"repos":["dannigt/NMTGMinor.lowLatency"],"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/multimodal-grounding-for-sequence-to-sequence","slug":"multimodal-grounding-for-sequence-to-sequence","title":"Multimodal Grounding for Sequence-to-Sequence Speech Recognition","date":"2018-11-09","arxiv_id":"1811.03865","repositories_listed":1,"syntology":null},{"url":"/paper/syllable-based-sequence-to-sequence-speech","slug":"syllable-based-sequence-to-sequence-speech","title":"Syllable-Based Sequence-to-Sequence Speech Recognition with the Transformer in Mandarin Chinese","date":"2018-04-28","arxiv_id":"1804.10752","repositories_listed":1,"syntology":null},{"url":"/paper/sequence-to-sequence-models-can-directly","slug":"sequence-to-sequence-models-can-directly","title":"Sequence-to-Sequence Models Can Directly Translate Foreign Speech","date":"2017-03-24","arxiv_id":"1703.08581","repositories_listed":1,"syntology":null},{"url":null,"slug":"rasr2-the-rwth-asr-toolkit-for-generic","title":"RASR2: The RWTH ASR Toolkit for Generic Sequence-to-sequence Speech Recognition","date":"2023-05-28","arxiv_id":"2305.17782","repositories_listed":0,"syntology":null},{"url":null,"slug":"avoid-overthinking-in-self-supervised-models","title":"Avoid Overthinking in Self-Supervised Models for Speech Recognition","date":"2022-11-01","arxiv_id":"2211.08989","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-agnostic-code-switching-in-end-to","title":"Language-agnostic Code-Switching in Sequence-To-Sequence Speech Recognition","date":"2022-10-17","arxiv_id":"2210.08992","repositories_listed":0,"syntology":null},{"url":null,"slug":"supervised-adaptation-of-sequence-to-sequence","title":"Supervised Adaptation of Sequence-to-Sequence Speech Recognition Systems using Batch-Weighting","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-whole-context-to-sequence-to","title":"Integrating Knowledge into End-to-End Speech Recognition from External Text-Only Data","date":"2019-12-04","arxiv_id":"1912.01777","repositories_listed":0,"syntology":null},{"url":null,"slug":"191013296","title":"Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation","date":"2019-10-29","arxiv_id":"1910.13296","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-pre-traing-for-sequence-to","title":"Unsupervised pre-training for sequence to sequence speech recognition","date":"2019-10-28","arxiv_id":"1910.12418","repositories_listed":0,"syntology":null},{"url":null,"slug":"learn-spelling-from-teachers-transferring","title":"Learn Spelling from Teachers: Transferring Knowledge from Language Models to Sequence-to-Sequence Speech Recognition","date":"2019-07-13","arxiv_id":"1907.06017","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-to-sequence-speech-recognition-with","title":"Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions","date":"2019-04-04","arxiv_id":"1904.02619","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequence-level-knowledge-distillation-for","title":"Sequence-Level Knowledge Distillation for Model Compression of Attention-based Sequence-to-Sequence Speech Recognition","date":"2018-11-12","arxiv_id":"1811.04531","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-multilingual-sequence-to-sequence","title":"Analysis of Multilingual Sequence-to-Sequence speech recognition systems","date":"2018-11-07","arxiv_id":"1811.03451","repositories_listed":0,"syntology":null},{"url":null,"slug":"language-model-integration-based-on-memory","title":"Language model integration based on memory control for sequence to sequence speech recognition","date":"2018-11-06","arxiv_id":"1811.02162","repositories_listed":0,"syntology":null},{"url":null,"slug":"multilingual-sequence-to-sequence-speech","title":"Multilingual sequence-to-sequence speech recognition: architecture, transfer learning, and language modeling","date":"2018-10-04","arxiv_id":"1810.03459","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-scale-alignment-and-contextual-history","title":"Multi-scale Alignment and Contextual History for Attention Mechanism in Sequence-to-sequence Model","date":"2018-07-22","arxiv_id":"1807.08280","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparison-of-modeling-units-in-sequence-to","title":"A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinese","date":"2018-05-16","arxiv_id":"1805.06239","repositories_listed":0,"syntology":null}],"syntology_records":2,"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":2,"papers_where_code_ran_first_page":"/task/sequence-to-sequence-speech-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":"ran","page":1,"of":1,"url":"/task/sequence-to-sequence-speech-recognition/papers/ran/1","json":"/task/sequence-to-sequence-speech-recognition/papers/ran/1.json","rows":2}],"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":"ff1b8a18954b28f864e03fa079d6a5f35ca75dc281e0cce61cd469019e150f09","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}