{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NFRBJ2GDUZQUHAOD4HHVBBZAIN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1f1f24b42fa85cc6bc6ac29faf2a331dfeee99ab803aa84385a7389d8d01e61d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-23T06:08:13Z","title_canon_sha256":"d7f4d6997a1715b41352c8d321a5abfc359a3d147d5f6ffe454d6b70fa1ff863"},"schema_version":"1.0","source":{"id":"2305.13716","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13716","created_at":"2026-07-05T06:57:23Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13716v3","created_at":"2026-07-05T06:57:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13716","created_at":"2026-07-05T06:57:23Z"},{"alias_kind":"pith_short_12","alias_value":"NFRBJ2GDUZQU","created_at":"2026-07-05T06:57:23Z"},{"alias_kind":"pith_short_16","alias_value":"NFRBJ2GDUZQUHAOD","created_at":"2026-07-05T06:57:23Z"},{"alias_kind":"pith_short_8","alias_value":"NFRBJ2GD","created_at":"2026-07-05T06:57:23Z"}],"graph_snapshots":[{"event_id":"sha256:3367bb8cac12fd4c23fa71d5a77fe9d3a729701ae58550284706cf395ac08d14","target":"graph","created_at":"2026-07-05T06:57:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.13716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fan Yu, Lei Xie, Pengcheng Guo, Qian Chen, Shiliang Zhang, Yangze Li, Yuhao Liang","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-23T06:08:13Z","title":"BA-SOT: Boundary-Aware Serialized Output Training for Multi-Talker ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13716","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1b709489032e3418348ad062ee9295e40481f9b2ad5e7f57ac623d428c037b01","target":"record","created_at":"2026-07-05T06:57:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1f1f24b42fa85cc6bc6ac29faf2a331dfeee99ab803aa84385a7389d8d01e61d","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-23T06:08:13Z","title_canon_sha256":"d7f4d6997a1715b41352c8d321a5abfc359a3d147d5f6ffe454d6b70fa1ff863"},"schema_version":"1.0","source":{"id":"2305.13716","kind":"arxiv","version":3}},"canonical_sha256":"696214e8c3a6614381c3e1cf5087204378ad1092f394f2e468986eb9cfc3a1e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"696214e8c3a6614381c3e1cf5087204378ad1092f394f2e468986eb9cfc3a1e3","first_computed_at":"2026-07-05T06:57:23.150607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:57:23.150607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lG7rFrKSo9yRneQDKB9RL0nz6XypTdcCFOqfM9j7vV47K4IJQ9BDNcGa/h89GIjJzS62ex54qd5Yi1DLttCWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:57:23.151082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13716","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b709489032e3418348ad062ee9295e40481f9b2ad5e7f57ac623d428c037b01","sha256:3367bb8cac12fd4c23fa71d5a77fe9d3a729701ae58550284706cf395ac08d14"],"state_sha256":"3a7d4ba096a722b402d45704eb56019c90f2cb7bf0c94938b4780966f053ada6"}