{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BSQA6OLVONN5CVUAPZ45DIH2JE","short_pith_number":"pith:BSQA6OLV","schema_version":"1.0","canonical_sha256":"0ca00f3975735bd156807e79d1a0fa493fbc1eedf826ef621406b7d4631c6eeb","source":{"kind":"arxiv","id":"2502.02683","version":1},"attestation_state":"computed","paper":{"title":"Streaming Speaker Change Detection and Gender Classification for Transducer-Based Multi-Talker Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aswin Shanmugam Subramanian, Jian Xue, Jinyu Li, Junkun Chen, Naoyuki Kanda, Peidong Wang, Sunit Sivasankaran, Xiaofei Wang, Xiong Xiao, Yong Zhao","submitted_at":"2025-02-04T19:50:15Z","abstract_excerpt":"Streaming multi-talker speech translation is a task that involves not only generating accurate and fluent translations with low latency but also recognizing when a speaker change occurs and what the speaker's gender is. Speaker change information can be used to create audio prompts for a zero-shot text-to-speech system, and gender can help to select speaker profiles in a conventional text-to-speech model. We propose to tackle streaming speaker change detection and gender classification by incorporating speaker embeddings into a transducer-based streaming end-to-end speech translation model. Ou"},"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":"2502.02683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-04T19:50:15Z","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"title_canon_sha256":"446099063ae582e39d6eec7b509b68e37e6ceb5fe68e9a06bfed16c5df0c5d08","abstract_canon_sha256":"e79d00f5f6dda6d0488b8a60d381c6b1bf7e529183a65c94fbc93eb356547e71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:53.479529Z","signature_b64":"dpMgzram6hdCI0IXEQJ7CH0HejRhxpyLXO8obieWim/aW9Ej+FTrCZghX17QnZSyQ7N9z0rPewRFH/sA+yFxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ca00f3975735bd156807e79d1a0fa493fbc1eedf826ef621406b7d4631c6eeb","last_reissued_at":"2026-07-05T10:09:53.478961Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:53.478961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Speaker Change Detection and Gender Classification for Transducer-Based Multi-Talker Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Aswin Shanmugam Subramanian, Jian Xue, Jinyu Li, Junkun Chen, Naoyuki Kanda, Peidong Wang, Sunit Sivasankaran, Xiaofei Wang, Xiong Xiao, Yong Zhao","submitted_at":"2025-02-04T19:50:15Z","abstract_excerpt":"Streaming multi-talker speech translation is a task that involves not only generating accurate and fluent translations with low latency but also recognizing when a speaker change occurs and what the speaker's gender is. Speaker change information can be used to create audio prompts for a zero-shot text-to-speech system, and gender can help to select speaker profiles in a conventional text-to-speech model. We propose to tackle streaming speaker change detection and gender classification by incorporating speaker embeddings into a transducer-based streaming end-to-end speech translation model. Ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02683","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/2502.02683/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":"2502.02683","created_at":"2026-07-05T10:09:53.479031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02683v1","created_at":"2026-07-05T10:09:53.479031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02683","created_at":"2026-07-05T10:09:53.479031+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSQA6OLVONN5","created_at":"2026-07-05T10:09:53.479031+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSQA6OLVONN5CVUA","created_at":"2026-07-05T10:09:53.479031+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSQA6OLV","created_at":"2026-07-05T10:09:53.479031+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/BSQA6OLVONN5CVUAPZ45DIH2JE","json":"https://pith.science/pith/BSQA6OLVONN5CVUAPZ45DIH2JE.json","graph_json":"https://pith.science/api/pith-number/BSQA6OLVONN5CVUAPZ45DIH2JE/graph.json","events_json":"https://pith.science/api/pith-number/BSQA6OLVONN5CVUAPZ45DIH2JE/events.json","paper":"https://pith.science/paper/BSQA6OLV"},"agent_actions":{"view_html":"https://pith.science/pith/BSQA6OLVONN5CVUAPZ45DIH2JE","download_json":"https://pith.science/pith/BSQA6OLVONN5CVUAPZ45DIH2JE.json","view_paper":"https://pith.science/paper/BSQA6OLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02683&json=true","fetch_graph":"https://pith.science/api/pith-number/BSQA6OLVONN5CVUAPZ45DIH2JE/graph.json","fetch_events":"https://pith.science/api/pith-number/BSQA6OLVONN5CVUAPZ45DIH2JE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSQA6OLVONN5CVUAPZ45DIH2JE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSQA6OLVONN5CVUAPZ45DIH2JE/action/storage_attestation","attest_author":"https://pith.science/pith/BSQA6OLVONN5CVUAPZ45DIH2JE/action/author_attestation","sign_citation":"https://pith.science/pith/BSQA6OLVONN5CVUAPZ45DIH2JE/action/citation_signature","submit_replication":"https://pith.science/pith/BSQA6OLVONN5CVUAPZ45DIH2JE/action/replication_record"}},"created_at":"2026-07-05T10:09:53.479031+00:00","updated_at":"2026-07-05T10:09:53.479031+00:00"}