{"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/voice-activity-projection-self-supervised","title":"Voice Activity Projection: Self-supervised Learning of Turn-taking Events","arxiv_id":"2205.09812","date":"2022-05-19","proceeding":null,"authors":["Erik Ekstedt","Gabriel Skantze"],"abstract":"The modeling of turn-taking in dialog can be viewed as the modeling of the dynamics of voice activity of the interlocutors. We extend prior work and define the predictive task of Voice Activity Projection, a general, self-supervised objective, as a way to train turn-taking models without the need of labeled data. We highlight a theoretical weakness with prior approaches, arguing for the need of modeling the dependency of voice activity events in the projection window. We propose four zero-shot tasks, related to the prediction of upcoming turn-shifts and backchannels, and show that the proposed model outperforms prior work.","url_abs":"https://arxiv.org/abs/2205.09812v1","url_pdf":"https://arxiv.org/pdf/2205.09812v1.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":"voice-activity-projection-self-supervised","repo_url":"https://github.com/erikekstedt/conv_ssl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"voice-activity-projection-self-supervised","repo_url":"https://github.com/erikekstedt/vap_turn_taking","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"voice-activity-projection-self-supervised","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":[{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2205.09812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.09812"}},"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/vap_turn_taking","reach":null},{"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_violates":2,"ran_fixture":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"d7e33acf478c32fc","entry":"bin_times_to_frames","repo":"erikekstedt/vap_turn_taking","repo_kind":"official","path":"vap_turn_taking/vap.py","file_url":"https://github.com/erikekstedt/vap_turn_taking/blob/HEAD/vap_turn_taking/vap.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d7e33acf478c32fc"}},{"code_sha256_prefix":"f04821dfa449cd68","entry":"get_curves","repo":"erikekstedt/conv_ssl","repo_kind":"official","path":"conv_ssl/evaluation/evaluation.py","file_url":"https://github.com/erikekstedt/conv_ssl/blob/HEAD/conv_ssl/evaluation/evaluation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f04821dfa449cd68"}},{"code_sha256_prefix":"cb8157c4f4236a85","entry":"probs_ind_backchannel","repo":"erikekstedt/vap_turn_taking","repo_kind":"official","path":"vap_turn_taking/vap.py","file_url":"https://github.com/erikekstedt/vap_turn_taking/blob/HEAD/vap_turn_taking/vap.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb8157c4f4236a85"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}