{"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/letter-based-speech-recognition-with-gated","title":"Letter-Based Speech Recognition with Gated ConvNets","arxiv_id":"1712.09444","date":"2017-12-22","proceeding":null,"authors":["Vitaliy Liptchinsky","Gabriel Synnaeve","Ronan Collobert"],"abstract":"In the recent literature, \"end-to-end\" speech systems often refer to\nletter-based acoustic models trained in a sequence-to-sequence manner, either\nvia a recurrent model or via a structured output learning approach (such as\nCTC). In contrast to traditional phone (or senone)-based approaches, these\n\"end-to-end'' approaches alleviate the need of word pronunciation modeling, and\ndo not require a \"forced alignment\" step at training time. Phone-based\napproaches remain however state of the art on classical benchmarks. In this\npaper, we propose a letter-based speech recognition system, leveraging a\nConvNet acoustic model. Key ingredients of the ConvNet are Gated Linear Units\nand high dropout. The ConvNet is trained to map audio sequences to their\ncorresponding letter transcriptions, either via a classical CTC approach, or\nvia a recent variant called ASG. Coupled with a simple decoder at inference\ntime, our system matches the best existing letter-based systems on WSJ (in word\nerror rate), and shows near state of the art performance on LibriSpeech.","url_abs":"http://arxiv.org/abs/1712.09444v2","url_pdf":"http://arxiv.org/pdf/1712.09444v2.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":"letter-based-speech-recognition-with-gated","repo_url":"https://github.com/MrMao/wav2letter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"letter-based-speech-recognition-with-gated","repo_url":"https://github.com/eric-erki/wav2letter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}}],"tasks":[{"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":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-librispeech-test-clean","task":"Speech Recognition","dataset":"LibriSpeech test-clean","model":"Gated ConvNets","rank_in_archive_order":56,"of":64,"metrics":{"Word Error Rate (WER)":"4.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1712.09444","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}