{"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":"/paper/state-of-the-art-speech-recognition-with","title":"State-of-the-art Speech Recognition With Sequence-to-Sequence Models","arxiv_id":"1712.01769","date":"2017-12-05","proceeding":null,"authors":["Chung-Cheng Chiu","Tara N. Sainath","Yonghui Wu","Rohit Prabhavalkar","Patrick Nguyen","Zhifeng Chen","Anjuli Kannan","Ron J. Weiss","Kanishka Rao","Ekaterina Gonina","Navdeep Jaitly","Bo Li","Jan Chorowski","Michiel Bacchiani"],"abstract":"Attention-based encoder-decoder architectures such as Listen, Attend, and\nSpell (LAS), subsume the acoustic, pronunciation and language model components\nof a traditional automatic speech recognition (ASR) system into a single neural\nnetwork. In previous work, we have shown that such architectures are comparable\nto state-of-theart ASR systems on dictation tasks, but it was not clear if such\narchitectures would be practical for more challenging tasks such as voice\nsearch. In this work, we explore a variety of structural and optimization\nimprovements to our LAS model which significantly improve performance. On the\nstructural side, we show that word piece models can be used instead of\ngraphemes. We also introduce a multi-head attention architecture, which offers\nimprovements over the commonly-used single-head attention. On the optimization\nside, we explore synchronous training, scheduled sampling, label smoothing, and\nminimum word error rate optimization, which are all shown to improve accuracy.\nWe present results with a unidirectional LSTM encoder for streaming\nrecognition. On a 12, 500 hour voice search task, we find that the proposed\nchanges improve the WER from 9.2% to 5.6%, while the best conventional system\nachieves 6.7%; on a dictation task our model achieves a WER of 4.1% compared to\n5% for the conventional system.","url_abs":"http://arxiv.org/abs/1712.01769v6","url_pdf":"http://arxiv.org/pdf/1712.01769v6.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"state-of-the-art-speech-recognition-with","repo_url":"https://github.com/30stomercury/Automatic_Speech_Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"state-of-the-art-speech-recognition-with","repo_url":"https://github.com/AzizCode92/Listen-Attend-and-Spell-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"state-of-the-art-speech-recognition-with","repo_url":"https://github.com/sooftware/End-to-end-Speech-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"state-of-the-art-speech-recognition-with","repo_url":"https://github.com/sooftware/OpenSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1712.01769","atlas_url":"https://app.syntology.ai/?focus=1712.01769","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1712.01769"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1712.01769\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1712.01769"},"call":"get_concepts_for_paper(arxiv_id=\"1712.01769\")"}],"by_repo":[{"repo":"30stomercury/Automatic_Speech_Recognition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"AzizCode92/Listen-Attend-and-Spell-Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sooftware/End-to-end-Speech-Recognition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"sooftware/OpenSpeech","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"a601d382f92cf8c4400fcec4ac16402c2dc897d1154cbc41347a8eac162aa871","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}