{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3WEGMVIBRZVEUUAQZBN7V2ZLZA","short_pith_number":"pith:3WEGMVIB","schema_version":"1.0","canonical_sha256":"dd886655018e6a4a5010c85bfaeb2bc82d2031de3677f80aba7f2fec27b08c9c","source":{"kind":"arxiv","id":"2306.16250","version":1},"attestation_state":"computed","paper":{"title":"MC-SpEx: Towards Effective Speaker Extraction with Multi-Scale Interfusion and Conditional Speaker Modulation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiuxin Lin, Jun Chen, Shulin He, Wei Rao, Yannan Wang, Yukai Ju, Zhiyong Wu, Zilin Wang","submitted_at":"2023-06-28T14:21:06Z","abstract_excerpt":"The previous SpEx+ has yielded outstanding performance in speaker extraction and attracted much attention. However, it still encounters inadequate utilization of multi-scale information and speaker embedding. To this end, this paper proposes a new effective speaker extraction system with multi-scale interfusion and conditional speaker modulation (ConSM), which is called MC-SpEx. First of all, we design the weight-share multi-scale fusers (ScaleFusers) for efficiently leveraging multi-scale information as well as ensuring consistency of the model's feature space. Then, to consider different sca"},"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":"2306.16250","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-06-28T14:21:06Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"32ea78d9df447b5df702f831ac8a5e8e609bc0750d342cb284f6f0299c91ff80","abstract_canon_sha256":"a7f8b987ac5db886b0b031f23c0f43d31fc80d101cb34a7c3a714edc7d54310f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:52.716478Z","signature_b64":"96y2Bjkt6jopdlAAdqrY3BbbngYOYWuH8YdZsqrDcX9MbiZtLWOQrJPjj/AFluU9zC/k/gdB37K4AK9a0DQKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd886655018e6a4a5010c85bfaeb2bc82d2031de3677f80aba7f2fec27b08c9c","last_reissued_at":"2026-07-05T06:25:52.716001Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:52.716001Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MC-SpEx: Towards Effective Speaker Extraction with Multi-Scale Interfusion and Conditional Speaker Modulation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Jiuxin Lin, Jun Chen, Shulin He, Wei Rao, Yannan Wang, Yukai Ju, Zhiyong Wu, Zilin Wang","submitted_at":"2023-06-28T14:21:06Z","abstract_excerpt":"The previous SpEx+ has yielded outstanding performance in speaker extraction and attracted much attention. However, it still encounters inadequate utilization of multi-scale information and speaker embedding. To this end, this paper proposes a new effective speaker extraction system with multi-scale interfusion and conditional speaker modulation (ConSM), which is called MC-SpEx. First of all, we design the weight-share multi-scale fusers (ScaleFusers) for efficiently leveraging multi-scale information as well as ensuring consistency of the model's feature space. Then, to consider different sca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.16250","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/2306.16250/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":"2306.16250","created_at":"2026-07-05T06:25:52.716060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.16250v1","created_at":"2026-07-05T06:25:52.716060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.16250","created_at":"2026-07-05T06:25:52.716060+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WEGMVIBRZVE","created_at":"2026-07-05T06:25:52.716060+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WEGMVIBRZVEUUAQ","created_at":"2026-07-05T06:25:52.716060+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WEGMVIB","created_at":"2026-07-05T06:25:52.716060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WEGMVIBRZVEUUAQZBN7V2ZLZA","json":"https://pith.science/pith/3WEGMVIBRZVEUUAQZBN7V2ZLZA.json","graph_json":"https://pith.science/api/pith-number/3WEGMVIBRZVEUUAQZBN7V2ZLZA/graph.json","events_json":"https://pith.science/api/pith-number/3WEGMVIBRZVEUUAQZBN7V2ZLZA/events.json","paper":"https://pith.science/paper/3WEGMVIB"},"agent_actions":{"view_html":"https://pith.science/pith/3WEGMVIBRZVEUUAQZBN7V2ZLZA","download_json":"https://pith.science/pith/3WEGMVIBRZVEUUAQZBN7V2ZLZA.json","view_paper":"https://pith.science/paper/3WEGMVIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.16250&json=true","fetch_graph":"https://pith.science/api/pith-number/3WEGMVIBRZVEUUAQZBN7V2ZLZA/graph.json","fetch_events":"https://pith.science/api/pith-number/3WEGMVIBRZVEUUAQZBN7V2ZLZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WEGMVIBRZVEUUAQZBN7V2ZLZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WEGMVIBRZVEUUAQZBN7V2ZLZA/action/storage_attestation","attest_author":"https://pith.science/pith/3WEGMVIBRZVEUUAQZBN7V2ZLZA/action/author_attestation","sign_citation":"https://pith.science/pith/3WEGMVIBRZVEUUAQZBN7V2ZLZA/action/citation_signature","submit_replication":"https://pith.science/pith/3WEGMVIBRZVEUUAQZBN7V2ZLZA/action/replication_record"}},"created_at":"2026-07-05T06:25:52.716060+00:00","updated_at":"2026-07-05T06:25:52.716060+00:00"}