{"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/eesen-end-to-end-speech-recognition-using","title":"EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decoding","arxiv_id":"1507.08240","date":"2015-07-29","proceeding":null,"authors":["Yajie Miao","Mohammad Gowayyed","Florian Metze"],"abstract":"The performance of automatic speech recognition (ASR) has improved\ntremendously due to the application of deep neural networks (DNNs). Despite\nthis progress, building a new ASR system remains a challenging task, requiring\nvarious resources, multiple training stages and significant expertise. This\npaper presents our Eesen framework which drastically simplifies the existing\npipeline to build state-of-the-art ASR systems. Acoustic modeling in Eesen\ninvolves learning a single recurrent neural network (RNN) predicting\ncontext-independent targets (phonemes or characters). To remove the need for\npre-generated frame labels, we adopt the connectionist temporal classification\n(CTC) objective function to infer the alignments between speech and label\nsequences. A distinctive feature of Eesen is a generalized decoding approach\nbased on weighted finite-state transducers (WFSTs), which enables the efficient\nincorporation of lexicons and language models into CTC decoding. Experiments\nshow that compared with the standard hybrid DNN systems, Eesen achieves\ncomparable word error rates (WERs), while at the same time speeding up decoding\nsignificantly.","url_abs":"http://arxiv.org/abs/1507.08240v3","url_pdf":"http://arxiv.org/pdf/1507.08240v3.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":"eesen-end-to-end-speech-recognition-using","repo_url":"https://github.com/yajiemiao/eesen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"eesen-end-to-end-speech-recognition-using","repo_url":"https://github.com/jb1999/eesen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"eesen-end-to-end-speech-recognition-using","repo_url":"https://github.com/srvk/eesen","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"eesen-end-to-end-speech-recognition-using","repo_url":"https://gitlab.com/Jaco-Assistant/finstreder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1507.08240","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}