{"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/attention-based-models-for-speech-recognition","title":"Attention-Based Models for Speech Recognition","arxiv_id":"1506.07503","date":"2015-06-24","proceeding":"NeurIPS 2015 12","authors":["Jan Chorowski","Dzmitry Bahdanau","Dmitriy Serdyuk","Kyunghyun Cho","Yoshua Bengio"],"abstract":"Recurrent sequence generators conditioned on input data through an attention\nmechanism have recently shown very good performance on a range of tasks in-\ncluding machine translation, handwriting synthesis and image caption gen-\neration. We extend the attention-mechanism with features needed for speech\nrecognition. We show that while an adaptation of the model used for machine\ntranslation in reaches a competitive 18.7% phoneme error rate (PER) on the\nTIMIT phoneme recognition task, it can only be applied to utterances which are\nroughly as long as the ones it was trained on. We offer a qualitative\nexplanation of this failure and propose a novel and generic method of adding\nlocation-awareness to the attention mechanism to alleviate this issue. The new\nmethod yields a model that is robust to long inputs and achieves 18% PER in\nsingle utterances and 20% in 10-times longer (repeated) utterances. Finally, we\npropose a change to the at- tention mechanism that prevents it from\nconcentrating too much on single frames, which further reduces PER to 17.6%\nlevel.","url_abs":"http://arxiv.org/abs/1506.07503v1","url_pdf":"http://arxiv.org/pdf/1506.07503v1.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":"attention-based-models-for-speech-recognition","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":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/Alexander-H-Liu/End-to-end-ASR-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/CKRC24/Listen-and-Translate","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/biyoml/End-to-End-Mandarin-ASR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/biyoml/Pytorch-End-to-End-ASR-on-TIMIT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/jackjhliu/End-to-End-Mandarin-ASR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/jackjhliu/Pytorch-End-to-End-ASR-on-TIMIT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/mnm-rnd/elsa-voice-asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/msalhab96/SpeeQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/neil-zeng/asr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/s3prl/End-to-end-ASR-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"attention-based-models-for-speech-recognition","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":"attention-based-models-for-speech-recognition","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"}},{"paper_slug":"attention-based-models-for-speech-recognition","repo_url":"https://github.com/sooftware/nlp-attentions","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"phoneme-recognition","task_name":"Phoneme Recognition"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"location-sensitive-attention","method_name":"Location Sensitive Attention"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[{"slug":"location-sensitive-attention","name":"Location Sensitive Attention","full_name":"Location Sensitive Attention"}],"results":[{"leaderboard":"/sota/speech-recognition-on-timit","task":"Speech Recognition","dataset":"TIMIT","model":"Bi-RNN + Attention","rank_in_archive_order":17,"of":22,"metrics":{"Percentage error":"17.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.07503","atlas_url":"https://app.syntology.ai/?focus=1506.07503","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":"1506.07503"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1506.07503\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1506.07503"},"call":"get_concepts_for_paper(arxiv_id=\"1506.07503\")"}],"by_repo":[{"repo":"30stomercury/Automatic_Speech_Recognition","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"Alexander-H-Liu/End-to-end-ASR-Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1609.06773"],"harvested_for_calls":[{"arxiv_id":"1609.06773","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.06773"},"call":"get_harvested_code_for_paper(arxiv_id=\"1609.06773\")"}]},{"repo":"CKRC24/Listen-and-Translate","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"biyoml/End-to-End-Mandarin-ASR","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"biyoml/Pytorch-End-to-End-ASR-on-TIMIT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jackjhliu/End-to-End-Mandarin-ASR","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"jackjhliu/Pytorch-End-to-End-ASR-on-TIMIT","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"mnm-rnd/elsa-voice-asr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"msalhab96/SpeeQ","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2206.00888"],"harvested_for_calls":[{"arxiv_id":"2206.00888","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2206.00888"},"call":"get_harvested_code_for_paper(arxiv_id=\"2206.00888\")"}]},{"repo":"neil-zeng/asr","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1609.06773"],"harvested_for_calls":[{"arxiv_id":"1609.06773","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.06773"},"call":"get_harvested_code_for_paper(arxiv_id=\"1609.06773\")"}]},{"repo":"s3prl/End-to-end-ASR-Pytorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1609.06773"],"harvested_for_calls":[{"arxiv_id":"1609.06773","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.06773"},"call":"get_harvested_code_for_paper(arxiv_id=\"1609.06773\")"}]},{"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},{"repo":"sooftware/nlp-attentions","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"5e37ec6e7298e37167820059b60d4c30c287850374502ed2a982948a3b79a6f2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}