{"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 (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":7,"of":7,"tagged_in_all":22,"items":[{"url":"/paper/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","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":0,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/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","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_unverified":0,"n_pointer_only":0}},{"url":"/paper/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","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","title":"Sequence-to-Sequence Models Can Directly Translate Foreign Speech","date":"2017-03-24","arxiv_id":"1703.08581","repositories_listed":1,"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"},"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":"2026-09-24T18:15:14+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; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"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"}}