{"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/real-time-and-continuous-turn-taking","title":"Real-time and Continuous Turn-taking Prediction Using Voice Activity Projection","arxiv_id":"2401.04868","date":"2024-01-10","proceeding":null,"authors":["Koji Inoue","Bing'er Jiang","Erik Ekstedt","Tatsuya Kawahara","Gabriel Skantze"],"abstract":"A demonstration of a real-time and continuous turn-taking prediction system is presented. The system is based on a voice activity projection (VAP) model, which directly maps dialogue stereo audio to future voice activities. The VAP model includes contrastive predictive coding (CPC) and self-attention transformers, followed by a cross-attention transformer. We examine the effect of the input context audio length and demonstrate that the proposed system can operate in real-time with CPU settings, with minimal performance degradation.","url_abs":"https://arxiv.org/abs/2401.04868v1","url_pdf":"https://arxiv.org/pdf/2401.04868v1.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":"real-time-and-continuous-turn-taking","repo_url":"https://github.com/ErikEkstedt/VoiceActivityProjection","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"real-time-and-continuous-turn-taking","repo_url":"https://github.com/inokoj/VAP-Realtime","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"CPU"}],"methods":[{"method_slug":"contrastive-predictive-coding","method_name":"Contrastive Predictive Coding"},{"method_slug":"infonce","method_name":"InfoNCE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}