{"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/target-conversation-extraction-source","title":"Target conversation extraction: Source separation using turn-taking dynamics","arxiv_id":"2407.11277","date":"2024-07-15","proceeding":null,"authors":["Tuochao Chen","Qirui Wang","Bohan Wu","Malek Itani","Sefik Emre Eskimez","Takuya Yoshioka","Shyamnath Gollakota"],"abstract":"Extracting the speech of participants in a conversation amidst interfering speakers and noise presents a challenging problem. In this paper, we introduce the novel task of target conversation extraction, where the goal is to extract the audio of a target conversation based on the speaker embedding of one of its participants. To accomplish this, we propose leveraging temporal patterns inherent in human conversations, particularly turn-taking dynamics, which uniquely characterize speakers engaged in conversation and distinguish them from interfering speakers and noise. Using neural networks, we show the feasibility of our approach on English and Mandarin conversation datasets. In the presence of interfering speakers, our results show an 8.19 dB improvement in signal-to-noise ratio for 2-speaker conversations and a 7.92 dB improvement for 2-4-speaker conversations. Code, dataset available at https://github.com/chentuochao/Target-Conversation-Extraction.","url_abs":"https://arxiv.org/abs/2407.11277v2","url_pdf":"https://arxiv.org/pdf/2407.11277v2.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":"target-conversation-extraction-source","repo_url":"https://github.com/chentuochao/target-conversation-extraction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.11277","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.11277"}},"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/chentuochao/target-conversation-extraction","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":11,"unverified":1},"by_repo_kind":{"official":{"samples":12,"ran":11,"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":"a0208c2aa866774d","entry":"calculate_cosine_similarity","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"eval_conversation.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/eval_conversation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0208c2aa866774d"}},{"code_sha256_prefix":"d427b8df3a56508a","entry":"filter_set_by_keys","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"datasets/dataset_loader.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/datasets/dataset_loader.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d427b8df3a56508a"}},{"code_sha256_prefix":"6083727b41952440","entry":"get_envelope","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"convert_AMI2Libri.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/convert_AMI2Libri.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6083727b41952440"}},{"code_sha256_prefix":"60539ba4504bfe7d","entry":"get_random_mic_positions","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"datasets/dataset_util.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/datasets/dataset_util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60539ba4504bfe7d"}},{"code_sha256_prefix":"e8c863bc61c7255a","entry":"high_pass_filter","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"convert_AMI2Libri.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/convert_AMI2Libri.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e8c863bc61c7255a"}},{"code_sha256_prefix":"63c5cc839a76504a","entry":"import_attr","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63c5cc839a76504a"}},{"code_sha256_prefix":"f22b1d22bc27279d","entry":"load_net","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f22b1d22bc27279d"}},{"code_sha256_prefix":"a2ea924d9b7f0fa1","entry":"mixing","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"datasets/generate_dataset.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/datasets/generate_dataset.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2ea924d9b7f0fa1"}},{"code_sha256_prefix":"032038059574b300","entry":"moving_average","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"convert_AMI2Libri.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/convert_AMI2Libri.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"032038059574b300"}},{"code_sha256_prefix":"6af82b66048558cc","entry":"overlap_duration_check","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"eval_conversation.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/eval_conversation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6af82b66048558cc"}},{"code_sha256_prefix":"7e2c6b8c214572ae","entry":"point_in_box","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"eval_conversation.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/eval_conversation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7e2c6b8c214572ae"}},{"code_sha256_prefix":"8470ce8d00caec6c","entry":"load_net_torch","repo":"chentuochao/target-conversation-extraction","repo_kind":"official","path":"src/utils.py","file_url":"https://github.com/chentuochao/target-conversation-extraction/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","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":"8470ce8d00caec6c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}