{"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/learning-when-to-speak-latency-and-quality","title":"Learning When to Speak: Latency and Quality Trade-offs for Simultaneous Speech-to-Speech Translation with Offline Models","arxiv_id":"2306.01201","date":"2023-06-01","proceeding":null,"authors":["Liam Dugan","Anshul Wadhawan","Kyle Spence","Chris Callison-Burch","Morgan McGuire","Victor Zordan"],"abstract":"Recent work in speech-to-speech translation (S2ST) has focused primarily on offline settings, where the full input utterance is available before any output is given. This, however, is not reasonable in many real-world scenarios. In latency-sensitive applications, rather than waiting for the full utterance, translations should be spoken as soon as the information in the input is present. In this work, we introduce a system for simultaneous S2ST targeting real-world use cases. Our system supports translation from 57 languages to English with tunable parameters for dynamically adjusting the latency of the output -- including four policies for determining when to speak an output sequence. We show that these policies achieve offline-level accuracy with minimal increases in latency over a Greedy (wait-$k$) baseline. We open-source our evaluation code and interactive test script to aid future SimulS2ST research and application development.","url_abs":"https://arxiv.org/abs/2306.01201v1","url_pdf":"https://arxiv.org/pdf/2306.01201v1.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":"learning-when-to-speak-latency-and-quality","repo_url":"https://github.com/liamdugan/speech-to-speech","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"simultaneous-speech-to-speech-translation","task_name":"Simultaneous Speech-to-Speech Translation"},{"task_slug":"speech-to-speech-translation","task_name":"Speech-to-Speech Translation"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}