{"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/multimodal-continuous-turn-taking-prediction","title":"Multimodal Continuous Turn-Taking Prediction Using Multiscale RNNs","arxiv_id":"1808.10785","date":"2018-08-31","proceeding":null,"authors":["Matthew Roddy","Gabriel Skantze","Naomi Harte"],"abstract":"In human conversational interactions, turn-taking exchanges can be\ncoordinated using cues from multiple modalities. To design spoken dialog\nsystems that can conduct fluid interactions it is desirable to incorporate cues\nfrom separate modalities into turn-taking models. We propose that there is an\nappropriate temporal granularity at which modalities should be modeled. We\ndesign a multiscale RNN architecture to model modalities at separate timescales\nin a continuous manner. Our results show that modeling linguistic and acoustic\nfeatures at separate temporal rates can be beneficial for turn-taking modeling.\nWe also show that our approach can be used to incorporate gaze features into\nturn-taking models.","url_abs":"http://arxiv.org/abs/1808.10785v1","url_pdf":"http://arxiv.org/pdf/1808.10785v1.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":"multimodal-continuous-turn-taking-prediction","repo_url":"https://github.com/mattroddy/lstm_turn_taking_prediction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1808.10785","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}