{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SF3ZAGKARDBB7LYFF4XDRBODLS","short_pith_number":"pith:SF3ZAGKA","schema_version":"1.0","canonical_sha256":"917790194088c21faf052f2e3885c35ca5165d49a8e11aaf6237c65ad343196c","source":{"kind":"arxiv","id":"2401.03697","version":2},"attestation_state":"computed","paper":{"title":"An audio-quality-based multi-strategy approach for target speaker extraction in the MISP 2023 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"He Wang, Jiayao Sun, Lei Xie, Ning Jiang, Pengcheng Guo, Quan Lu, Runduo Han, Weiming Xu, Xiaopeng Yan","submitted_at":"2024-01-08T07:04:30Z","abstract_excerpt":"This paper describes our audio-quality-based multi-strategy approach for the audio-visual target speaker extraction (AVTSE) task in the Multi-modal Information based Speech Processing (MISP) 2023 Challenge. Specifically, our approach adopts different extraction strategies based on the audio quality, striking a balance between interference removal and speech preservation, which benifits the back-end automatic speech recognition (ASR) systems. Experiments show that our approach achieves a character error rate (CER) of 24.2% and 33.2% on the Dev and Eval set, respectively, obtaining the second pl"},"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":"2401.03697","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-01-08T07:04:30Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"68fd31cfe1302ce4f07c1fbb51163dcbe042345a345e424b466f8b8477ce175c","abstract_canon_sha256":"b3403e39033261dc8760286d6d0ea16c7124acc73492887ca4324ce8220c1c33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:14.027993Z","signature_b64":"mtWZnWH7yLHC+1Mx0QphCw00SCdFLk//lj9GbEs8oKVNVB5x7YEqZI1KfxwXO17VEd2bWuyS5TWKLuK8bj0wAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917790194088c21faf052f2e3885c35ca5165d49a8e11aaf6237c65ad343196c","last_reissued_at":"2026-07-05T07:53:14.027513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:14.027513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An audio-quality-based multi-strategy approach for target speaker extraction in the MISP 2023 Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"He Wang, Jiayao Sun, Lei Xie, Ning Jiang, Pengcheng Guo, Quan Lu, Runduo Han, Weiming Xu, Xiaopeng Yan","submitted_at":"2024-01-08T07:04:30Z","abstract_excerpt":"This paper describes our audio-quality-based multi-strategy approach for the audio-visual target speaker extraction (AVTSE) task in the Multi-modal Information based Speech Processing (MISP) 2023 Challenge. Specifically, our approach adopts different extraction strategies based on the audio quality, striking a balance between interference removal and speech preservation, which benifits the back-end automatic speech recognition (ASR) systems. Experiments show that our approach achieves a character error rate (CER) of 24.2% and 33.2% on the Dev and Eval set, respectively, obtaining the second pl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.03697","kind":"arxiv","version":2},"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/2401.03697/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":"2401.03697","created_at":"2026-07-05T07:53:14.027571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.03697v2","created_at":"2026-07-05T07:53:14.027571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.03697","created_at":"2026-07-05T07:53:14.027571+00:00"},{"alias_kind":"pith_short_12","alias_value":"SF3ZAGKARDBB","created_at":"2026-07-05T07:53:14.027571+00:00"},{"alias_kind":"pith_short_16","alias_value":"SF3ZAGKARDBB7LYF","created_at":"2026-07-05T07:53:14.027571+00:00"},{"alias_kind":"pith_short_8","alias_value":"SF3ZAGKA","created_at":"2026-07-05T07:53:14.027571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22013","citing_title":"Overlap-Adaptive Hybrid Speaker Diarization and ASR-Aware Observation Addition for MISP 2025 Challenge","ref_index":25,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SF3ZAGKARDBB7LYFF4XDRBODLS","json":"https://pith.science/pith/SF3ZAGKARDBB7LYFF4XDRBODLS.json","graph_json":"https://pith.science/api/pith-number/SF3ZAGKARDBB7LYFF4XDRBODLS/graph.json","events_json":"https://pith.science/api/pith-number/SF3ZAGKARDBB7LYFF4XDRBODLS/events.json","paper":"https://pith.science/paper/SF3ZAGKA"},"agent_actions":{"view_html":"https://pith.science/pith/SF3ZAGKARDBB7LYFF4XDRBODLS","download_json":"https://pith.science/pith/SF3ZAGKARDBB7LYFF4XDRBODLS.json","view_paper":"https://pith.science/paper/SF3ZAGKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.03697&json=true","fetch_graph":"https://pith.science/api/pith-number/SF3ZAGKARDBB7LYFF4XDRBODLS/graph.json","fetch_events":"https://pith.science/api/pith-number/SF3ZAGKARDBB7LYFF4XDRBODLS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SF3ZAGKARDBB7LYFF4XDRBODLS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SF3ZAGKARDBB7LYFF4XDRBODLS/action/storage_attestation","attest_author":"https://pith.science/pith/SF3ZAGKARDBB7LYFF4XDRBODLS/action/author_attestation","sign_citation":"https://pith.science/pith/SF3ZAGKARDBB7LYFF4XDRBODLS/action/citation_signature","submit_replication":"https://pith.science/pith/SF3ZAGKARDBB7LYFF4XDRBODLS/action/replication_record"}},"created_at":"2026-07-05T07:53:14.027571+00:00","updated_at":"2026-07-05T07:53:14.027571+00:00"}