{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NFRBJ2GDUZQUHAOD4HHVBBZAIN","short_pith_number":"pith:NFRBJ2GD","schema_version":"1.0","canonical_sha256":"696214e8c3a6614381c3e1cf5087204378ad1092f394f2e468986eb9cfc3a1e3","source":{"kind":"arxiv","id":"2305.13716","version":3},"attestation_state":"computed","paper":{"title":"BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fan Yu, Lei Xie, Pengcheng Guo, Qian Chen, Shiliang Zhang, Yangze Li, Yuhao Liang","submitted_at":"2023-05-23T06:08:13Z","abstract_excerpt":"The recently proposed serialized output training (SOT) simplifies multi-talker automatic speech recognition (ASR) by generating speaker transcriptions separated by a special token. However, frequent speaker changes can make speaker change prediction difficult. To address this, we propose boundary-aware serialized output training (BA-SOT), which explicitly incorporates boundary knowledge into the decoder via a speaker change detection task and boundary constraint loss. We also introduce a two-stage connectionist temporal classification (CTC) strategy that incorporates token-level SOT CTC to res"},"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":"2305.13716","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-23T06:08:13Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"d7f4d6997a1715b41352c8d321a5abfc359a3d147d5f6ffe454d6b70fa1ff863","abstract_canon_sha256":"1f1f24b42fa85cc6bc6ac29faf2a331dfeee99ab803aa84385a7389d8d01e61d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:23.151082Z","signature_b64":"lG7rFrKSo9yRneQDKB9RL0nz6XypTdcCFOqfM9j7vV47K4IJQ9BDNcGa/h89GIjJzS62ex54qd5Yi1DLttCWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"696214e8c3a6614381c3e1cf5087204378ad1092f394f2e468986eb9cfc3a1e3","last_reissued_at":"2026-07-05T06:57:23.150607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:23.150607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Fan Yu, Lei Xie, Pengcheng Guo, Qian Chen, Shiliang Zhang, Yangze Li, Yuhao Liang","submitted_at":"2023-05-23T06:08:13Z","abstract_excerpt":"The recently proposed serialized output training (SOT) simplifies multi-talker automatic speech recognition (ASR) by generating speaker transcriptions separated by a special token. However, frequent speaker changes can make speaker change prediction difficult. To address this, we propose boundary-aware serialized output training (BA-SOT), which explicitly incorporates boundary knowledge into the decoder via a speaker change detection task and boundary constraint loss. We also introduce a two-stage connectionist temporal classification (CTC) strategy that incorporates token-level SOT CTC to res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13716","kind":"arxiv","version":3},"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/2305.13716/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":"2305.13716","created_at":"2026-07-05T06:57:23.150669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13716v3","created_at":"2026-07-05T06:57:23.150669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13716","created_at":"2026-07-05T06:57:23.150669+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFRBJ2GDUZQU","created_at":"2026-07-05T06:57:23.150669+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFRBJ2GDUZQUHAOD","created_at":"2026-07-05T06:57:23.150669+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFRBJ2GD","created_at":"2026-07-05T06:57:23.150669+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/NFRBJ2GDUZQUHAOD4HHVBBZAIN","json":"https://pith.science/pith/NFRBJ2GDUZQUHAOD4HHVBBZAIN.json","graph_json":"https://pith.science/api/pith-number/NFRBJ2GDUZQUHAOD4HHVBBZAIN/graph.json","events_json":"https://pith.science/api/pith-number/NFRBJ2GDUZQUHAOD4HHVBBZAIN/events.json","paper":"https://pith.science/paper/NFRBJ2GD"},"agent_actions":{"view_html":"https://pith.science/pith/NFRBJ2GDUZQUHAOD4HHVBBZAIN","download_json":"https://pith.science/pith/NFRBJ2GDUZQUHAOD4HHVBBZAIN.json","view_paper":"https://pith.science/paper/NFRBJ2GD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13716&json=true","fetch_graph":"https://pith.science/api/pith-number/NFRBJ2GDUZQUHAOD4HHVBBZAIN/graph.json","fetch_events":"https://pith.science/api/pith-number/NFRBJ2GDUZQUHAOD4HHVBBZAIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFRBJ2GDUZQUHAOD4HHVBBZAIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFRBJ2GDUZQUHAOD4HHVBBZAIN/action/storage_attestation","attest_author":"https://pith.science/pith/NFRBJ2GDUZQUHAOD4HHVBBZAIN/action/author_attestation","sign_citation":"https://pith.science/pith/NFRBJ2GDUZQUHAOD4HHVBBZAIN/action/citation_signature","submit_replication":"https://pith.science/pith/NFRBJ2GDUZQUHAOD4HHVBBZAIN/action/replication_record"}},"created_at":"2026-07-05T06:57:23.150669+00:00","updated_at":"2026-07-05T06:57:23.150669+00:00"}