{"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/sequence-transduction-with-recurrent-neural","title":"Sequence Transduction with Recurrent Neural Networks","arxiv_id":"1211.3711","date":"2012-11-14","proceeding":null,"authors":["Alex Graves"],"abstract":"Many machine learning tasks can be expressed as the transformation---or\n\\emph{transduction}---of input sequences into output sequences: speech\nrecognition, machine translation, protein secondary structure prediction and\ntext-to-speech to name but a few. One of the key challenges in sequence\ntransduction is learning to represent both the input and output sequences in a\nway that is invariant to sequential distortions such as shrinking, stretching\nand translating. Recurrent neural networks (RNNs) are a powerful sequence\nlearning architecture that has proven capable of learning such representations.\nHowever RNNs traditionally require a pre-defined alignment between the input\nand output sequences to perform transduction. This is a severe limitation since\n\\emph{finding} the alignment is the most difficult aspect of many sequence\ntransduction problems. Indeed, even determining the length of the output\nsequence is often challenging. This paper introduces an end-to-end,\nprobabilistic sequence transduction system, based entirely on RNNs, that is in\nprinciple able to transform any input sequence into any finite, discrete output\nsequence. Experimental results for phoneme recognition are provided on the\nTIMIT speech corpus.","url_abs":"http://arxiv.org/abs/1211.3711v1","url_pdf":"http://arxiv.org/pdf/1211.3711v1.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":"sequence-transduction-with-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":"sequence-transduction-with-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":"sequence-transduction-with-recurrent-neural","repo_url":"https://github.com/TensorSpeech/TensorFlowASR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"sequence-transduction-with-recurrent-neural","repo_url":"https://github.com/fd873630/RNN-Transducer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sequence-transduction-with-recurrent-neural","repo_url":"https://github.com/iamjanvijay/rnnt_decoder_cuda","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"sequence-transduction-with-recurrent-neural","repo_url":"https://github.com/msalhab96/SpeeQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"sequence-transduction-with-recurrent-neural","repo_url":"https://github.com/mejanvijay/RNN-Transducer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","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":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1211.3711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1211.3711"}},"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/TensorSpeech/TensorFlowASR","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mejanvijay/RNN-Transducer","reach":{"status":"ok","spdx":"MIT"}},{"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/HawkAaron/warp-transducer","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iamjanvijay/rnnt_decoder_cuda","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fd873630/RNN-Transducer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/msalhab96/SpeeQ","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"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":"f2ed78972b234ea0","entry":"create_one_hot","repo":"mejanvijay/RNN-Transducer","repo_kind":"listed","path":"source/sample_train.py","file_url":"https://github.com/mejanvijay/RNN-Transducer/blob/HEAD/source/sample_train.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":"f2ed78972b234ea0"}},{"code_sha256_prefix":"c285f006e044f9d3","entry":"extract_diagonals","repo":"mejanvijay/RNN-Transducer","repo_kind":"listed","path":"source/rnnt_loss.py","file_url":"https://github.com/mejanvijay/RNN-Transducer/blob/HEAD/source/rnnt_loss.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":"c285f006e044f9d3"}},{"code_sha256_prefix":"269c2e21a00b24f4","entry":"nan_to_zero","repo":"mejanvijay/RNN-Transducer","repo_kind":"listed","path":"source/rnnt_loss.py","file_url":"https://github.com/mejanvijay/RNN-Transducer/blob/HEAD/source/rnnt_loss.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":"269c2e21a00b24f4"}},{"code_sha256_prefix":"cef7042d2f8d6021","entry":"reduce_logsumexp","repo":"mejanvijay/RNN-Transducer","repo_kind":"listed","path":"source/rnnt_loss.py","file_url":"https://github.com/mejanvijay/RNN-Transducer/blob/HEAD/source/rnnt_loss.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":"cef7042d2f8d6021"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}