{"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/how-much-does-prosody-help-turn-taking","title":"How Much Does Prosody Help Turn-taking? Investigations using Voice Activity Projection Models","arxiv_id":"2209.05161","date":"2022-09-12","proceeding":"SIGDIAL (ACL) 2022 9","authors":["Erik Ekstedt","Gabriel Skantze"],"abstract":"Turn-taking is a fundamental aspect of human communication and can be described as the ability to take turns, project upcoming turn shifts, and supply backchannels at appropriate locations throughout a conversation. In this work, we investigate the role of prosody in turn-taking using the recently proposed Voice Activity Projection model, which incrementally models the upcoming speech activity of the interlocutors in a self-supervised manner, without relying on explicit annotation of turn-taking events, or the explicit modeling of prosodic features. Through manipulation of the speech signal, we investigate how these models implicitly utilize prosodic information. We show that these systems learn to utilize various prosodic aspects of speech both on aggregate quantitative metrics of long-form conversations and on single utterances specifically designed to depend on prosody.","url_abs":"https://arxiv.org/abs/2209.05161v1","url_pdf":"https://arxiv.org/pdf/2209.05161v1.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":"how-much-does-prosody-help-turn-taking","repo_url":"https://github.com/erikekstedt/conv_ssl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"how-much-does-prosody-help-turn-taking","repo_url":"https://github.com/ErikEkstedt/VoiceActivityProjection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.05161","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.05161"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ErikEkstedt/VoiceActivityProjection","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/erikekstedt/conv_ssl","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":8},"by_repo_kind":{"listed":{"samples":9,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1a33f1ad866748f1","entry":"ffn_block","repo":"ErikEkstedt/VoiceActivityProjection","repo_kind":"listed","path":"vap/modules.py","file_url":"https://github.com/ErikEkstedt/VoiceActivityProjection/blob/HEAD/vap/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a33f1ad866748f1"}},{"code_sha256_prefix":"e665e68c17d3ac72","entry":"get_backward_hook","repo":"ErikEkstedt/VoiceActivityProjection","repo_kind":"listed","path":"analyzes/model_params_grad.py","file_url":"https://github.com/ErikEkstedt/VoiceActivityProjection/blob/HEAD/analyzes/model_params_grad.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e665e68c17d3ac72"}},{"code_sha256_prefix":"73113a8ee3f05e4f","entry":"get_cnn_layer","repo":"ErikEkstedt/VoiceActivityProjection","repo_kind":"listed","path":"vap/encoder_components.py","file_url":"https://github.com/ErikEkstedt/VoiceActivityProjection/blob/HEAD/vap/encoder_components.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73113a8ee3f05e4f"}},{"code_sha256_prefix":"085ea8c81b8bac59","entry":"get_forward_hook","repo":"ErikEkstedt/VoiceActivityProjection","repo_kind":"listed","path":"analyzes/model_params_grad.py","file_url":"https://github.com/ErikEkstedt/VoiceActivityProjection/blob/HEAD/analyzes/model_params_grad.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"085ea8c81b8bac59"}},{"code_sha256_prefix":"03a206f26bc91a00","entry":"load_older_state_dict","repo":"ErikEkstedt/VoiceActivityProjection","repo_kind":"listed","path":"vap/model.py","file_url":"https://github.com/ErikEkstedt/VoiceActivityProjection/blob/HEAD/vap/model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"03a206f26bc91a00"}},{"code_sha256_prefix":"a4f10a84c432b9f2","entry":"plot_output_and_grads","repo":"ErikEkstedt/VoiceActivityProjection","repo_kind":"listed","path":"analyzes/model_params_grad.py","file_url":"https://github.com/ErikEkstedt/VoiceActivityProjection/blob/HEAD/analyzes/model_params_grad.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4f10a84c432b9f2"}},{"code_sha256_prefix":"cae3f1bbfe8fb064","entry":"sample_to_time","repo":"ErikEkstedt/VoiceActivityProjection","repo_kind":"listed","path":"vap/audio.py","file_url":"https://github.com/ErikEkstedt/VoiceActivityProjection/blob/HEAD/vap/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cae3f1bbfe8fb064"}},{"code_sha256_prefix":"66b85f1f634fb17d","entry":"time_to_frames","repo":"ErikEkstedt/VoiceActivityProjection","repo_kind":"listed","path":"vap/audio.py","file_url":"https://github.com/ErikEkstedt/VoiceActivityProjection/blob/HEAD/vap/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"66b85f1f634fb17d"}},{"code_sha256_prefix":"8ba61f078091d2e7","entry":"time_to_samples","repo":"ErikEkstedt/VoiceActivityProjection","repo_kind":"listed","path":"vap/audio.py","file_url":"https://github.com/ErikEkstedt/VoiceActivityProjection/blob/HEAD/vap/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8ba61f078091d2e7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}