{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BSQA6OLVONN5CVUAPZ45DIH2JE","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":"e79d00f5f6dda6d0488b8a60d381c6b1bf7e529183a65c94fbc93eb356547e71","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-04T19:50:15Z","title_canon_sha256":"446099063ae582e39d6eec7b509b68e37e6ceb5fe68e9a06bfed16c5df0c5d08"},"schema_version":"1.0","source":{"id":"2502.02683","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.02683","created_at":"2026-07-05T10:09:53Z"},{"alias_kind":"arxiv_version","alias_value":"2502.02683v1","created_at":"2026-07-05T10:09:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02683","created_at":"2026-07-05T10:09:53Z"},{"alias_kind":"pith_short_12","alias_value":"BSQA6OLVONN5","created_at":"2026-07-05T10:09:53Z"},{"alias_kind":"pith_short_16","alias_value":"BSQA6OLVONN5CVUA","created_at":"2026-07-05T10:09:53Z"},{"alias_kind":"pith_short_8","alias_value":"BSQA6OLV","created_at":"2026-07-05T10:09:53Z"}],"graph_snapshots":[{"event_id":"sha256:4145f1920e778afea0987a60dc9b85fd717287b9a49f38455b6008f112227e5a","target":"graph","created_at":"2026-07-05T10:09:53Z","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/2502.02683/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aswin Shanmugam Subramanian, Jian Xue, Jinyu Li, Junkun Chen, Naoyuki Kanda, Peidong Wang, Sunit Sivasankaran, Xiaofei Wang, Xiong Xiao, Yong Zhao","cross_cats":["cs.AI","cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-04T19:50:15Z","title":"Streaming Speaker Change Detection and Gender Classification for Transducer-Based Multi-Talker Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02683","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:c117b9df2556713c6aa26baa3d2d9bd5b384edacbcc4bb00bead89213efe2b07","target":"record","created_at":"2026-07-05T10:09:53Z","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":"e79d00f5f6dda6d0488b8a60d381c6b1bf7e529183a65c94fbc93eb356547e71","cross_cats_sorted":["cs.AI","cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-04T19:50:15Z","title_canon_sha256":"446099063ae582e39d6eec7b509b68e37e6ceb5fe68e9a06bfed16c5df0c5d08"},"schema_version":"1.0","source":{"id":"2502.02683","kind":"arxiv","version":1}},"canonical_sha256":"0ca00f3975735bd156807e79d1a0fa493fbc1eedf826ef621406b7d4631c6eeb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ca00f3975735bd156807e79d1a0fa493fbc1eedf826ef621406b7d4631c6eeb","first_computed_at":"2026-07-05T10:09:53.478961Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:53.478961Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dpMgzram6hdCI0IXEQJ7CH0HejRhxpyLXO8obieWim/aW9Ej+FTrCZghX17QnZSyQ7N9z0rPewRFH/sA+yFxCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:53.479529Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.02683","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c117b9df2556713c6aa26baa3d2d9bd5b384edacbcc4bb00bead89213efe2b07","sha256:4145f1920e778afea0987a60dc9b85fd717287b9a49f38455b6008f112227e5a"],"state_sha256":"230ffb4c71add913454c825388e9f7927ab5ae0f4077688345a0c725d075064e"}