{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4JEBIBFJ7YZWRLNFWEREKR34T3","short_pith_number":"pith:4JEBIBFJ","schema_version":"1.0","canonical_sha256":"e2481404a9fe3368ada5b12245477c9eed1a04d7e0037bca934a4d7c01b2dfbe","source":{"kind":"arxiv","id":"2506.07515","version":1},"attestation_state":"computed","paper":{"title":"Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Asahi Sakuma, Hiroaki Sato, Ryuga Sugano, Tadashi Kumano, Tetsuji Ogawa, Yoshihiko Kawai","submitted_at":"2025-06-09T07:43:43Z","abstract_excerpt":"This paper presents a novel framework for multi-talker automatic speech recognition without the need for auxiliary information. Serialized Output Training (SOT), a widely used approach, suffers from recognition errors due to speaker assignment failures. Although incorporating auxiliary information, such as token-level timestamps, can improve recognition accuracy, extracting such information from natural conversational speech remains challenging. To address this limitation, we propose Speaker-Distinguishable CTC (SD-CTC), an extension of CTC that jointly assigns a token and its corresponding sp"},"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":"2506.07515","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-06-09T07:43:43Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"4f2af16ff213cdc55dfc1701d4614d01b9dab1fe2edc1e9b0bc8206e3a5e5d09","abstract_canon_sha256":"57c733b1619bbadaba52ea9a0cb120f761462599e3e51e1311caea851ccf65a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:28.660920Z","signature_b64":"UivWI/564upUp/oNGl4Do5r4A+DMpXfRuBwuoJxyCiMOpp6eHh2cOKw38JYqj/DuuCqCSwKdi9PaVJRmw/F8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2481404a9fe3368ada5b12245477c9eed1a04d7e0037bca934a4d7c01b2dfbe","last_reissued_at":"2026-07-05T11:18:28.660429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:28.660429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Asahi Sakuma, Hiroaki Sato, Ryuga Sugano, Tadashi Kumano, Tetsuji Ogawa, Yoshihiko Kawai","submitted_at":"2025-06-09T07:43:43Z","abstract_excerpt":"This paper presents a novel framework for multi-talker automatic speech recognition without the need for auxiliary information. Serialized Output Training (SOT), a widely used approach, suffers from recognition errors due to speaker assignment failures. Although incorporating auxiliary information, such as token-level timestamps, can improve recognition accuracy, extracting such information from natural conversational speech remains challenging. To address this limitation, we propose Speaker-Distinguishable CTC (SD-CTC), an extension of CTC that jointly assigns a token and its corresponding sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07515","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/2506.07515/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":"2506.07515","created_at":"2026-07-05T11:18:28.660484+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.07515v1","created_at":"2026-07-05T11:18:28.660484+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07515","created_at":"2026-07-05T11:18:28.660484+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JEBIBFJ7YZW","created_at":"2026-07-05T11:18:28.660484+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JEBIBFJ7YZWRLNF","created_at":"2026-07-05T11:18:28.660484+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JEBIBFJ","created_at":"2026-07-05T11:18:28.660484+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07515","citing_title":"Speaker-Distinguishable CTC: Learning Speaker Distinction Using CTC for Multi-Talker Speech Recognition","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JEBIBFJ7YZWRLNFWEREKR34T3","json":"https://pith.science/pith/4JEBIBFJ7YZWRLNFWEREKR34T3.json","graph_json":"https://pith.science/api/pith-number/4JEBIBFJ7YZWRLNFWEREKR34T3/graph.json","events_json":"https://pith.science/api/pith-number/4JEBIBFJ7YZWRLNFWEREKR34T3/events.json","paper":"https://pith.science/paper/4JEBIBFJ"},"agent_actions":{"view_html":"https://pith.science/pith/4JEBIBFJ7YZWRLNFWEREKR34T3","download_json":"https://pith.science/pith/4JEBIBFJ7YZWRLNFWEREKR34T3.json","view_paper":"https://pith.science/paper/4JEBIBFJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.07515&json=true","fetch_graph":"https://pith.science/api/pith-number/4JEBIBFJ7YZWRLNFWEREKR34T3/graph.json","fetch_events":"https://pith.science/api/pith-number/4JEBIBFJ7YZWRLNFWEREKR34T3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JEBIBFJ7YZWRLNFWEREKR34T3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JEBIBFJ7YZWRLNFWEREKR34T3/action/storage_attestation","attest_author":"https://pith.science/pith/4JEBIBFJ7YZWRLNFWEREKR34T3/action/author_attestation","sign_citation":"https://pith.science/pith/4JEBIBFJ7YZWRLNFWEREKR34T3/action/citation_signature","submit_replication":"https://pith.science/pith/4JEBIBFJ7YZWRLNFWEREKR34T3/action/replication_record"}},"created_at":"2026-07-05T11:18:28.660484+00:00","updated_at":"2026-07-05T11:18:28.660484+00:00"}