{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6XG6X5NJFZWIUE4AG6WCO2Z7MZ","short_pith_number":"pith:6XG6X5NJ","schema_version":"1.0","canonical_sha256":"f5cdebf5a92e6c8a138037ac276b3f664b818742cc2c93c4054d92fd049a5ade","source":{"kind":"arxiv","id":"2306.02273","version":1},"attestation_state":"computed","paper":{"title":"End-to-End Joint Target and Non-Target Speakers ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Akihiko Takashima, Atsushi Ando, Hiroshi Sato, Keita Suzuki, Mana Ihori, Mihiro Uchida, Naoki Makishima, Nobukatsu Hojo, Ryo Masumura, Saki Mizuno, Satoshi Suzuki, Taiga Yamane, Takafumi Moriya, Tomohiro Tanaka, Yoshihiko Yamazaki","submitted_at":"2023-06-04T06:38:15Z","abstract_excerpt":"This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker's speech while identifying whether they are target or non-target speakers from multi-talker overlapped speech. Target-speaker ASR systems are a promising way to only transcribe a target speaker's speech by enrolling the target speaker's information. However, in conversational ASR applications, transcribing both the target speaker's speech and non-target speakers' ones is often required to understand interactive information. To naturally consider both target and non-target speakers in a "},"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":"2306.02273","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T06:38:15Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"c08c7c125fa00915a89da6b3cfdabe0379db17566c0960ff8eef6644a118c8ef","abstract_canon_sha256":"0897e2bc273baab12875bf8538171bed02d4ad4d70822abcc2c4047ff9b4e78c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:15.182654Z","signature_b64":"er052wSgU4bHf5WoVfOhwjUedpPCHYvug76vSnfbPVUwKADOu74xwWTAlspo4yRMbQrApr+7hW0Xy7F5IYPLBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5cdebf5a92e6c8a138037ac276b3f664b818742cc2c93c4054d92fd049a5ade","last_reissued_at":"2026-07-05T06:17:15.182291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:15.182291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"End-to-End Joint Target and Non-Target Speakers ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Akihiko Takashima, Atsushi Ando, Hiroshi Sato, Keita Suzuki, Mana Ihori, Mihiro Uchida, Naoki Makishima, Nobukatsu Hojo, Ryo Masumura, Saki Mizuno, Satoshi Suzuki, Taiga Yamane, Takafumi Moriya, Tomohiro Tanaka, Yoshihiko Yamazaki","submitted_at":"2023-06-04T06:38:15Z","abstract_excerpt":"This paper proposes a novel automatic speech recognition (ASR) system that can transcribe individual speaker's speech while identifying whether they are target or non-target speakers from multi-talker overlapped speech. Target-speaker ASR systems are a promising way to only transcribe a target speaker's speech by enrolling the target speaker's information. However, in conversational ASR applications, transcribing both the target speaker's speech and non-target speakers' ones is often required to understand interactive information. To naturally consider both target and non-target speakers in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02273","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/2306.02273/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":"2306.02273","created_at":"2026-07-05T06:17:15.182364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02273v1","created_at":"2026-07-05T06:17:15.182364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02273","created_at":"2026-07-05T06:17:15.182364+00:00"},{"alias_kind":"pith_short_12","alias_value":"6XG6X5NJFZWI","created_at":"2026-07-05T06:17:15.182364+00:00"},{"alias_kind":"pith_short_16","alias_value":"6XG6X5NJFZWIUE4A","created_at":"2026-07-05T06:17:15.182364+00:00"},{"alias_kind":"pith_short_8","alias_value":"6XG6X5NJ","created_at":"2026-07-05T06:17:15.182364+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/6XG6X5NJFZWIUE4AG6WCO2Z7MZ","json":"https://pith.science/pith/6XG6X5NJFZWIUE4AG6WCO2Z7MZ.json","graph_json":"https://pith.science/api/pith-number/6XG6X5NJFZWIUE4AG6WCO2Z7MZ/graph.json","events_json":"https://pith.science/api/pith-number/6XG6X5NJFZWIUE4AG6WCO2Z7MZ/events.json","paper":"https://pith.science/paper/6XG6X5NJ"},"agent_actions":{"view_html":"https://pith.science/pith/6XG6X5NJFZWIUE4AG6WCO2Z7MZ","download_json":"https://pith.science/pith/6XG6X5NJFZWIUE4AG6WCO2Z7MZ.json","view_paper":"https://pith.science/paper/6XG6X5NJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02273&json=true","fetch_graph":"https://pith.science/api/pith-number/6XG6X5NJFZWIUE4AG6WCO2Z7MZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6XG6X5NJFZWIUE4AG6WCO2Z7MZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6XG6X5NJFZWIUE4AG6WCO2Z7MZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6XG6X5NJFZWIUE4AG6WCO2Z7MZ/action/storage_attestation","attest_author":"https://pith.science/pith/6XG6X5NJFZWIUE4AG6WCO2Z7MZ/action/author_attestation","sign_citation":"https://pith.science/pith/6XG6X5NJFZWIUE4AG6WCO2Z7MZ/action/citation_signature","submit_replication":"https://pith.science/pith/6XG6X5NJFZWIUE4AG6WCO2Z7MZ/action/replication_record"}},"created_at":"2026-07-05T06:17:15.182364+00:00","updated_at":"2026-07-05T06:17:15.182364+00:00"}