{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZRNTQG32XSQBGHD6O6SWFFDPH5","short_pith_number":"pith:ZRNTQG32","schema_version":"1.0","canonical_sha256":"cc5b381b7abca0131c7e77a562946f3f51fe8fa199b14e5ccf8746021a1ea0ac","source":{"kind":"arxiv","id":"2409.08881","version":1},"attestation_state":"computed","paper":{"title":"Data Efficient Child-Adult Speaker Diarization with Simulated Conversations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Anfeng Xu, Catherine Lord, Helen Tager-Flusberg, Shrikanth Narayanan, Tiantian Feng","submitted_at":"2024-09-13T14:45:18Z","abstract_excerpt":"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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2409.08881","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-13T14:45:18Z","cross_cats_sorted":[],"title_canon_sha256":"f6f22ff82e9aae6be3ad250e4404ce2ec2c280c0ebbdeae5f74ce34e093d7586","abstract_canon_sha256":"892325bd90acc96b182534bb699826ae437908c6a17d34974d4139d6fcfef828"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:05.078754Z","signature_b64":"aq2dJvH0MMerU+XeknszJ0LcW3MkOlmLr3tdchNoo0Qi88AHxQPkFbwmWRdLzwxSDyjKRr6J3umVeTFQ5XyUBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc5b381b7abca0131c7e77a562946f3f51fe8fa199b14e5ccf8746021a1ea0ac","last_reissued_at":"2026-07-05T11:20:05.078201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:05.078201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Efficient Child-Adult Speaker Diarization with Simulated Conversations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Anfeng Xu, Catherine Lord, Helen Tager-Flusberg, Shrikanth Narayanan, Tiantian Feng","submitted_at":"2024-09-13T14:45:18Z","abstract_excerpt":"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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08881","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.08881/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.08881","created_at":"2026-07-05T11:20:05.078285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08881v1","created_at":"2026-07-05T11:20:05.078285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08881","created_at":"2026-07-05T11:20:05.078285+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRNTQG32XSQB","created_at":"2026-07-05T11:20:05.078285+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRNTQG32XSQBGHD6","created_at":"2026-07-05T11:20:05.078285+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRNTQG32","created_at":"2026-07-05T11:20:05.078285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10761","citing_title":"Can Generic LLMs Help Analyze Child-adult Interactions Involving Children with Autism in Clinical Observation?","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRNTQG32XSQBGHD6O6SWFFDPH5","json":"https://pith.science/pith/ZRNTQG32XSQBGHD6O6SWFFDPH5.json","graph_json":"https://pith.science/api/pith-number/ZRNTQG32XSQBGHD6O6SWFFDPH5/graph.json","events_json":"https://pith.science/api/pith-number/ZRNTQG32XSQBGHD6O6SWFFDPH5/events.json","paper":"https://pith.science/paper/ZRNTQG32"},"agent_actions":{"view_html":"https://pith.science/pith/ZRNTQG32XSQBGHD6O6SWFFDPH5","download_json":"https://pith.science/pith/ZRNTQG32XSQBGHD6O6SWFFDPH5.json","view_paper":"https://pith.science/paper/ZRNTQG32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08881&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRNTQG32XSQBGHD6O6SWFFDPH5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRNTQG32XSQBGHD6O6SWFFDPH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRNTQG32XSQBGHD6O6SWFFDPH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRNTQG32XSQBGHD6O6SWFFDPH5/action/storage_attestation","attest_author":"https://pith.science/pith/ZRNTQG32XSQBGHD6O6SWFFDPH5/action/author_attestation","sign_citation":"https://pith.science/pith/ZRNTQG32XSQBGHD6O6SWFFDPH5/action/citation_signature","submit_replication":"https://pith.science/pith/ZRNTQG32XSQBGHD6O6SWFFDPH5/action/replication_record"}},"created_at":"2026-07-05T11:20:05.078285+00:00","updated_at":"2026-07-05T11:20:05.078285+00:00"}