{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5HTS2IICPGPV2DJ3ZR2PD37VP5","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":"153293bf635603002b2b6325b14d70be99ca937c5a7ae0ae2cec2e6075beaad6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-25T12:10:28Z","title_canon_sha256":"6155552dd5d9a30aba88abb3d64aab86838d7816c8c9a43f07ce2165ce8cf27f"},"schema_version":"1.0","source":{"id":"2305.15971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15971","created_at":"2026-07-05T06:13:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15971v1","created_at":"2026-07-05T06:13:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15971","created_at":"2026-07-05T06:13:58Z"},{"alias_kind":"pith_short_12","alias_value":"5HTS2IICPGPV","created_at":"2026-07-05T06:13:58Z"},{"alias_kind":"pith_short_16","alias_value":"5HTS2IICPGPV2DJ3","created_at":"2026-07-05T06:13:58Z"},{"alias_kind":"pith_short_8","alias_value":"5HTS2IIC","created_at":"2026-07-05T06:13:58Z"}],"graph_snapshots":[{"event_id":"sha256:81edb1cbbedcea235bb08ea24bb14b75cb30bbb781d44ca2b4022ab6275d9596","target":"graph","created_at":"2026-07-05T06:13:58Z","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/2305.15971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural transducer (RNNT)-based target-speaker speech recognition (TS-RNNT) directly transcribes a target speaker's voice from a multi-talker mixture. It is a promising approach for streaming applications because it does not incur the extra computation costs of a target speech extraction frontend, which is a critical barrier to quick response. TS-RNNT is trained end-to-end given the input speech (i.e., mixtures and enrollment speech) and reference transcriptions. The training mixtures are generally simulated by mixing single-talker signals, but conventional TS-RNNT training does not utilize sin","authors_text":"Atsunori Ogawa, Hiroshi Sato, Kohei Matsuura, Marc Delcroix, Ryo Masumura, Taichi Asami, Takafumi Moriya, Takanori Ashihara, Tomohiro Tanaka, Tsubasa Ochiai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-25T12:10:28Z","title":"Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15971","kind":"arxiv","version":1},"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:be7f42bfd0d72c8dc329a8b8f547f1a566acb678d383f8e0c768f5ed3fd37668","target":"record","created_at":"2026-07-05T06:13:58Z","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":"153293bf635603002b2b6325b14d70be99ca937c5a7ae0ae2cec2e6075beaad6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-25T12:10:28Z","title_canon_sha256":"6155552dd5d9a30aba88abb3d64aab86838d7816c8c9a43f07ce2165ce8cf27f"},"schema_version":"1.0","source":{"id":"2305.15971","kind":"arxiv","version":1}},"canonical_sha256":"e9e72d2102799f5d0d3bcc74f1eff57f4dbb4079c2c5bafad2e75bc2f667d870","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9e72d2102799f5d0d3bcc74f1eff57f4dbb4079c2c5bafad2e75bc2f667d870","first_computed_at":"2026-07-05T06:13:58.122913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:58.122913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GqVwssev/p6T2ky7+agOuBtAR5SDJ5dDRzTdOFmv7MrDC/K9E/atXMX53Pq66kTVGkRMntlDHuKaEbcVRFAoCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:58.123254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be7f42bfd0d72c8dc329a8b8f547f1a566acb678d383f8e0c768f5ed3fd37668","sha256:81edb1cbbedcea235bb08ea24bb14b75cb30bbb781d44ca2b4022ab6275d9596"],"state_sha256":"ecdad9cbd488d23a8f518313133484592cdb5b71543db39143ed53b231c28b55"}