{"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/wav2letter-an-end-to-end-convnet-based-speech","title":"Wav2Letter: an End-to-End ConvNet-based Speech Recognition System","arxiv_id":"1609.03193","date":"2016-09-11","proceeding":"arXiv 2016 9","authors":["Ronan Collobert","Christian Puhrsch","Gabriel Synnaeve"],"abstract":"This paper presents a simple end-to-end model for speech recognition,\ncombining a convolutional network based acoustic model and a graph decoding. It\nis trained to output letters, with transcribed speech, without the need for\nforce alignment of phonemes. We introduce an automatic segmentation criterion\nfor training from sequence annotation without alignment that is on par with CTC\nwhile being simpler. We show competitive results in word error rate on the\nLibrispeech corpus with MFCC features, and promising results from raw waveform.","url_abs":"http://arxiv.org/abs/1609.03193v2","url_pdf":"http://arxiv.org/pdf/1609.03193v2.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":"wav2letter-an-end-to-end-convnet-based-speech","repo_url":"https://github.com/CorrelAid/codingchallenge1020_team1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"wav2letter-an-end-to-end-convnet-based-speech","repo_url":"https://github.com/JuliusKunze/speechless","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"wav2letter-an-end-to-end-convnet-based-speech","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":"wav2letter-an-end-to-end-convnet-based-speech","repo_url":"https://github.com/ashwin9999/Capstone-Speech-to-SQL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"wav2letter-an-end-to-end-convnet-based-speech","repo_url":"https://github.com/ashwin9999/speech-recognition-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"wav2letter-an-end-to-end-convnet-based-speech","repo_url":"https://github.com/eric-erki/wav2letter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"unanswered"}},{"paper_slug":"wav2letter-an-end-to-end-convnet-based-speech","repo_url":"https://github.com/mailong25/vietnamese-speech-recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"wav2letter-an-end-to-end-convnet-based-speech","repo_url":"https://github.com/msalhab96/SpeeQ","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"wav2letter-an-end-to-end-convnet-based-speech","repo_url":"https://github.com/silversparro/wav2letter.pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"speech-recognition","task_name":"Speech Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.03193","atlas_url":"https://app.syntology.ai/?focus=1609.03193","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}