{"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/streaming-end-to-end-speech-recognition-for","title":"Streaming End-to-end Speech Recognition For Mobile Devices","arxiv_id":"1811.06621","date":"2018-11-15","proceeding":null,"authors":["Yanzhang He","Tara N. Sainath","Rohit Prabhavalkar","Ian McGraw","Raziel Alvarez","Ding Zhao","David Rybach","Anjuli Kannan","Yonghui Wu","Ruoming Pang","Qiao Liang","Deepti Bhatia","Yuan Shangguan","Bo Li","Golan Pundak","Khe Chai Sim","Tom Bagby","Shuo-Yiin Chang","Kanishka Rao","Alexander Gruenstein"],"abstract":"End-to-end (E2E) models, which directly predict output character sequences\ngiven input speech, are good candidates for on-device speech recognition. E2E\nmodels, however, present numerous challenges: In order to be truly useful, such\nmodels must decode speech utterances in a streaming fashion, in real time; they\nmust be robust to the long tail of use cases; they must be able to leverage\nuser-specific context (e.g., contact lists); and above all, they must be\nextremely accurate. In this work, we describe our efforts at building an E2E\nspeech recognizer using a recurrent neural network transducer. In experimental\nevaluations, we find that the proposed approach can outperform a conventional\nCTC-based model in terms of both latency and accuracy in a number of evaluation\ncategories.","url_abs":"http://arxiv.org/abs/1811.06621v1","url_pdf":"http://arxiv.org/pdf/1811.06621v1.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":"streaming-end-to-end-speech-recognition-for","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":"streaming-end-to-end-speech-recognition-for","repo_url":"https://github.com/gteu/reaptime-ppg-vc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"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=1811.06621","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}