{"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/data-efficient-child-adult-speaker","title":"Data Efficient Child-Adult Speaker Diarization with Simulated Conversations","arxiv_id":"2409.08881","date":"2024-09-13","proceeding":null,"authors":["Anfeng Xu","Tiantian Feng","Helen Tager-Flusberg","Catherine Lord","Shrikanth Narayanan"],"abstract":"Automating child speech analysis is crucial for applications such as neurocognitive assessments. Speaker diarization, which identifies ``who spoke when'', is an essential component of the automated analysis. However, publicly available child-adult speaker diarization solutions are scarce due to privacy concerns and a lack of annotated datasets, while manually annotating data for each scenario is both time-consuming and costly. To overcome these challenges, we propose a data-efficient solution by creating simulated child-adult conversations using AudioSet. We then train a Whisper Encoder-based model, achieving strong zero-shot performance on child-adult speaker diarization using real datasets. The model performance improves substantially when fine-tuned with only 30 minutes of real train data, with LoRA further improving the transfer learning performance. The source code and the child-adult speaker diarization model trained on simulated conversations are publicly available.","url_abs":"https://arxiv.org/abs/2409.08881v1","url_pdf":"https://arxiv.org/pdf/2409.08881v1.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":"data-efficient-child-adult-speaker","repo_url":"https://github.com/usc-sail/child-adult-diarization","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"speaker-diarization","task_name":"Speaker Diarization"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"speaker-diarization","task_name":"speaker-diarization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.08881","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.08881"}},"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/usc-sail/child-adult-diarization","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"f677a1fd568c2e3b","entry":"collate_fn","repo":"usc-sail/child-adult-diarization","repo_kind":"official","path":"whisper-modeling/dataset_classes/datasets.py","file_url":"https://github.com/usc-sail/child-adult-diarization/blob/HEAD/whisper-modeling/dataset_classes/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f677a1fd568c2e3b"}},{"code_sha256_prefix":"8161452ed1e1b3dc","entry":"label_map","repo":"usc-sail/child-adult-diarization","repo_kind":"official","path":"whisper-modeling/dataset_classes/preprocess.py","file_url":"https://github.com/usc-sail/child-adult-diarization/blob/HEAD/whisper-modeling/dataset_classes/preprocess.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8161452ed1e1b3dc"}},{"code_sha256_prefix":"06fe0dd113ba3d60","entry":"padding_cropping_audio","repo":"usc-sail/child-adult-diarization","repo_kind":"official","path":"whisper-modeling/dataset_classes/datasets.py","file_url":"https://github.com/usc-sail/child-adult-diarization/blob/HEAD/whisper-modeling/dataset_classes/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"06fe0dd113ba3d60"}},{"code_sha256_prefix":"e2f4827b035ebd30","entry":"prepare_mask","repo":"usc-sail/child-adult-diarization","repo_kind":"official","path":"whisper-modeling/models/whisper.py","file_url":"https://github.com/usc-sail/child-adult-diarization/blob/HEAD/whisper-modeling/models/whisper.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e2f4827b035ebd30"}},{"code_sha256_prefix":"fac6d3517cd4d773","entry":"mel_filters","repo":"usc-sail/child-adult-diarization","repo_kind":"official","path":"whisper-modeling/models/whisper.py","file_url":"https://github.com/usc-sail/child-adult-diarization/blob/HEAD/whisper-modeling/models/whisper.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fac6d3517cd4d773"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}