{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5HTS2IICPGPV2DJ3ZR2PD37VP5","short_pith_number":"pith:5HTS2IIC","schema_version":"1.0","canonical_sha256":"e9e72d2102799f5d0d3bcc74f1eff57f4dbb4079c2c5bafad2e75bc2f667d870","source":{"kind":"arxiv","id":"2305.15971","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Atsunori Ogawa, Hiroshi Sato, Kohei Matsuura, Marc Delcroix, Ryo Masumura, Taichi Asami, Takafumi Moriya, Takanori Ashihara, Tomohiro Tanaka, Tsubasa Ochiai","submitted_at":"2023-05-25T12:10:28Z","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"},"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":"2305.15971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2023-05-25T12:10:28Z","cross_cats_sorted":[],"title_canon_sha256":"6155552dd5d9a30aba88abb3d64aab86838d7816c8c9a43f07ce2165ce8cf27f","abstract_canon_sha256":"153293bf635603002b2b6325b14d70be99ca937c5a7ae0ae2cec2e6075beaad6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:58.123254Z","signature_b64":"GqVwssev/p6T2ky7+agOuBtAR5SDJ5dDRzTdOFmv7MrDC/K9E/atXMX53Pq66kTVGkRMntlDHuKaEbcVRFAoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9e72d2102799f5d0d3bcc74f1eff57f4dbb4079c2c5bafad2e75bc2f667d870","last_reissued_at":"2026-07-05T06:13:58.122913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:58.122913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Atsunori Ogawa, Hiroshi Sato, Kohei Matsuura, Marc Delcroix, Ryo Masumura, Taichi Asami, Takafumi Moriya, Takanori Ashihara, Tomohiro Tanaka, Tsubasa Ochiai","submitted_at":"2023-05-25T12:10:28Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15971","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/2305.15971/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":"2305.15971","created_at":"2026-07-05T06:13:58.122974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.15971v1","created_at":"2026-07-05T06:13:58.122974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15971","created_at":"2026-07-05T06:13:58.122974+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HTS2IICPGPV","created_at":"2026-07-05T06:13:58.122974+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HTS2IICPGPV2DJ3","created_at":"2026-07-05T06:13:58.122974+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HTS2IIC","created_at":"2026-07-05T06:13:58.122974+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/5HTS2IICPGPV2DJ3ZR2PD37VP5","json":"https://pith.science/pith/5HTS2IICPGPV2DJ3ZR2PD37VP5.json","graph_json":"https://pith.science/api/pith-number/5HTS2IICPGPV2DJ3ZR2PD37VP5/graph.json","events_json":"https://pith.science/api/pith-number/5HTS2IICPGPV2DJ3ZR2PD37VP5/events.json","paper":"https://pith.science/paper/5HTS2IIC"},"agent_actions":{"view_html":"https://pith.science/pith/5HTS2IICPGPV2DJ3ZR2PD37VP5","download_json":"https://pith.science/pith/5HTS2IICPGPV2DJ3ZR2PD37VP5.json","view_paper":"https://pith.science/paper/5HTS2IIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.15971&json=true","fetch_graph":"https://pith.science/api/pith-number/5HTS2IICPGPV2DJ3ZR2PD37VP5/graph.json","fetch_events":"https://pith.science/api/pith-number/5HTS2IICPGPV2DJ3ZR2PD37VP5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HTS2IICPGPV2DJ3ZR2PD37VP5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HTS2IICPGPV2DJ3ZR2PD37VP5/action/storage_attestation","attest_author":"https://pith.science/pith/5HTS2IICPGPV2DJ3ZR2PD37VP5/action/author_attestation","sign_citation":"https://pith.science/pith/5HTS2IICPGPV2DJ3ZR2PD37VP5/action/citation_signature","submit_replication":"https://pith.science/pith/5HTS2IICPGPV2DJ3ZR2PD37VP5/action/replication_record"}},"created_at":"2026-07-05T06:13:58.122974+00:00","updated_at":"2026-07-05T06:13:58.122974+00:00"}