{"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/when-can-i-speak-predicting-initiation-points","title":"When can I Speak? Predicting initiation points for spoken dialogue agents","arxiv_id":"2208.03812","date":"2022-08-07","proceeding":"SIGDIAL (ACL) 2022 9","authors":["Siyan Li","Ashwin Paranjape","Christopher D. Manning"],"abstract":"Current spoken dialogue systems initiate their turns after a long period of silence (700-1000ms), which leads to little real-time feedback, sluggish responses, and an overall stilted conversational flow. Humans typically respond within 200ms and successfully predicting initiation points in advance would allow spoken dialogue agents to do the same. In this work, we predict the lead-time to initiation using prosodic features from a pre-trained speech representation model (wav2vec 1.0) operating on user audio and word features from a pre-trained language model (GPT-2) operating on incremental transcriptions. To evaluate errors, we propose two metrics w.r.t. predicted and true lead times. We train and evaluate the models on the Switchboard Corpus and find that our method outperforms features from prior work on both metrics and vastly outperforms the common approach of waiting for 700ms of silence.","url_abs":"https://arxiv.org/abs/2208.03812v1","url_pdf":"https://arxiv.org/pdf/2208.03812v1.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":"when-can-i-speak-predicting-initiation-points","repo_url":"https://github.com/siyan-sylvia-li/icarus_final","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"spoken-dialogue-systems","task_name":"Spoken Dialogue Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2208.03812","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.03812"}},"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/siyan-sylvia-li/icarus_final","reach":null}],"summary":{"ran_fixture":6,"ran_honours":1},"by_repo_kind":{"official":{"samples":7,"ran":7,"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":"2cc631bc9a7dafea","entry":"bucket_ts_loss","repo":"siyan-sylvia-li/icarus_final","repo_kind":"official","path":"icarus_min_trainer.py","file_url":"https://github.com/siyan-sylvia-li/icarus_final/blob/HEAD/icarus_min_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2cc631bc9a7dafea"}},{"code_sha256_prefix":"87d7c55076c6cfc4","entry":"calc_da_loss","repo":"siyan-sylvia-li/icarus_final","repo_kind":"official","path":"icarus_heatmap_trainer.py","file_url":"https://github.com/siyan-sylvia-li/icarus_final/blob/HEAD/icarus_heatmap_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"87d7c55076c6cfc4"}},{"code_sha256_prefix":"a563b5d8b711445b","entry":"calc_loss","repo":"siyan-sylvia-li/icarus_final","repo_kind":"official","path":"icarus_gmm_trainer.py","file_url":"https://github.com/siyan-sylvia-li/icarus_final/blob/HEAD/icarus_gmm_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a563b5d8b711445b"}},{"code_sha256_prefix":"28b2e0c2fab85f9c","entry":"calc_loss","repo":"siyan-sylvia-li/icarus_final","repo_kind":"official","path":"icarus_heatmap_trainer.py","file_url":"https://github.com/siyan-sylvia-li/icarus_final/blob/HEAD/icarus_heatmap_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"28b2e0c2fab85f9c"}},{"code_sha256_prefix":"4d417aa3b42feb48","entry":"calc_loss","repo":"siyan-sylvia-li/icarus_final","repo_kind":"official","path":"icarus_min_trainer.py","file_url":"https://github.com/siyan-sylvia-li/icarus_final/blob/HEAD/icarus_min_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d417aa3b42feb48"}},{"code_sha256_prefix":"22a3fbffb874f01d","entry":"calc_loss_plot","repo":"siyan-sylvia-li/icarus_final","repo_kind":"official","path":"icarus_min_trainer.py","file_url":"https://github.com/siyan-sylvia-li/icarus_final/blob/HEAD/icarus_min_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22a3fbffb874f01d"}},{"code_sha256_prefix":"9f0be7bd096906fb","entry":"ce_da_loss","repo":"siyan-sylvia-li/icarus_final","repo_kind":"official","path":"icarus_gmm_trainer.py","file_url":"https://github.com/siyan-sylvia-li/icarus_final/blob/HEAD/icarus_gmm_trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f0be7bd096906fb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}