{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/speech-recognition-with-deep-recurrent-neural","title":"Speech Recognition with Deep Recurrent Neural Networks","arxiv_id":"1303.5778","date":"2013-03-22","proceeding":null,"authors":["Alex Graves","Abdel-rahman Mohamed","Geoffrey Hinton"],"abstract":"Recurrent neural networks (RNNs) are a powerful model for sequential data.\nEnd-to-end training methods such as Connectionist Temporal Classification make\nit possible to train RNNs for sequence labelling problems where the\ninput-output alignment is unknown. The combination of these methods with the\nLong Short-term Memory RNN architecture has proved particularly fruitful,\ndelivering state-of-the-art results in cursive handwriting recognition. However\nRNN performance in speech recognition has so far been disappointing, with\nbetter results returned by deep feedforward networks. This paper investigates\n\\emph{deep recurrent neural networks}, which combine the multiple levels of\nrepresentation that have proved so effective in deep networks with the flexible\nuse of long range context that empowers RNNs. When trained end-to-end with\nsuitable regularisation, we find that deep Long Short-term Memory RNNs achieve\na test set error of 17.7% on the TIMIT phoneme recognition benchmark, which to\nour knowledge is the best recorded score.","url_abs":"http://arxiv.org/abs/1303.5778v1","url_pdf":"http://arxiv.org/pdf/1303.5778v1.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":"speech-recognition-with-deep-recurrent-neural","repo_url":"https://github.com/1ytic/warp-rnnt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"speech-recognition-with-deep-recurrent-neural","repo_url":"https://github.com/HawkAaron/warp-transducer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"speech-recognition-with-deep-recurrent-neural","repo_url":"https://github.com/jeremyrchow/text-generation-kaggle","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"speech-recognition-with-deep-recurrent-neural","repo_url":"https://github.com/kahnchana/RNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"speech-recognition-with-deep-recurrent-neural","repo_url":"https://github.com/sooftware/OpenSpeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"handwriting-recognition","task_name":"Handwriting Recognition"},{"task_slug":"phoneme-recognition","task_name":"Phoneme Recognition"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-timit","task":"Speech Recognition","dataset":"TIMIT","model":"Bi-LSTM + skip connections w/ CTC","rank_in_archive_order":18,"of":22,"metrics":{"Percentage error":"17.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1303.5778","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1303.5778"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/1ytic/warp-rnnt","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sooftware/OpenSpeech","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HawkAaron/warp-transducer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kahnchana/RNN","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jeremyrchow/text-generation-kaggle","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1326b96281ef4a4f","entry":"gen_data","repo":"1ytic/warp-rnnt","repo_kind":"listed","path":"pytorch_binding/benchmark2.py","file_url":"https://github.com/1ytic/warp-rnnt/blob/HEAD/pytorch_binding/benchmark2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1326b96281ef4a4f"}},{"code_sha256_prefix":"948bbf41724d1f71","entry":"gen_data_from_real","repo":"1ytic/warp-rnnt","repo_kind":"listed","path":"pytorch_binding/benchmark2.py","file_url":"https://github.com/1ytic/warp-rnnt/blob/HEAD/pytorch_binding/benchmark2.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"948bbf41724d1f71"}},{"code_sha256_prefix":"4c403a94d4f70757","entry":"run_benchmark","repo":"1ytic/warp-rnnt","repo_kind":"listed","path":"pytorch_binding/benchmark.py","file_url":"https://github.com/1ytic/warp-rnnt/blob/HEAD/pytorch_binding/benchmark.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4c403a94d4f70757"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}