{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3LLCW3RU7OII42EK6VBWAAKECW","short_pith_number":"pith:3LLCW3RU","schema_version":"1.0","canonical_sha256":"dad62b6e34fb908e688af54360014415ab662015aa1386bbb82838c64f05b579","source":{"kind":"arxiv","id":"2606.13095","version":1},"attestation_state":"computed","paper":{"title":"Balancing ASR and diarization in end-to-end LLMs for multi-talker speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dandan Tu, Longshuai Xiao, Mengtian Li, Naijun Zheng, Sanli Tian, Yuke Lin, Zhiwei Lin","submitted_at":"2026-06-11T09:25:14Z","abstract_excerpt":"Multi-talker speech recognition is often addressed by combining automatic speech recognition (ASR) and speaker diarization in a pipeline system. Recently, LLM-based approaches have shown promise by jointly modeling semantic and speaker information, but they typically require large-scale multi-talker corpora that are costly to annotate. In this paper, we investigate how to efficiently train an LLM-based system with limited real-recorded data while maintaining high accuracy in speaker attribution. We propose several strategies: (1) a dual-encoder architecture to extract semantic and speaker feat"},"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":"2606.13095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-11T09:25:14Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"91d6016943e15c5caae12ca4751860e199e6fdf7d0a09b3456c9682889d020e9","abstract_canon_sha256":"599ef2e1a0bd0739d3df75d8e2c4ac2035cacd1e5bdc3f2d6fe8e49d0f158225"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-12T01:09:39.891747Z","signature_b64":"0dcd32rlPuiyQDt3sUKZrwWyZosJU0NAKMhN3wtyKkV63Gg9mh3t8QspQoW6q/sdrvvCtXug1xnBVu4lCFP6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dad62b6e34fb908e688af54360014415ab662015aa1386bbb82838c64f05b579","last_reissued_at":"2026-06-12T01:09:39.891110Z","signature_status":"signed_v1","first_computed_at":"2026-06-12T01:09:39.891110Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Balancing ASR and diarization in end-to-end LLMs for multi-talker speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dandan Tu, Longshuai Xiao, Mengtian Li, Naijun Zheng, Sanli Tian, Yuke Lin, Zhiwei Lin","submitted_at":"2026-06-11T09:25:14Z","abstract_excerpt":"Multi-talker speech recognition is often addressed by combining automatic speech recognition (ASR) and speaker diarization in a pipeline system. Recently, LLM-based approaches have shown promise by jointly modeling semantic and speaker information, but they typically require large-scale multi-talker corpora that are costly to annotate. In this paper, we investigate how to efficiently train an LLM-based system with limited real-recorded data while maintaining high accuracy in speaker attribution. We propose several strategies: (1) a dual-encoder architecture to extract semantic and speaker feat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13095","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/2606.13095/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":"2606.13095","created_at":"2026-06-12T01:09:39.891198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.13095v1","created_at":"2026-06-12T01:09:39.891198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13095","created_at":"2026-06-12T01:09:39.891198+00:00"},{"alias_kind":"pith_short_12","alias_value":"3LLCW3RU7OII","created_at":"2026-06-12T01:09:39.891198+00:00"},{"alias_kind":"pith_short_16","alias_value":"3LLCW3RU7OII42EK","created_at":"2026-06-12T01:09:39.891198+00:00"},{"alias_kind":"pith_short_8","alias_value":"3LLCW3RU","created_at":"2026-06-12T01:09:39.891198+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/3LLCW3RU7OII42EK6VBWAAKECW","json":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW.json","graph_json":"https://pith.science/api/pith-number/3LLCW3RU7OII42EK6VBWAAKECW/graph.json","events_json":"https://pith.science/api/pith-number/3LLCW3RU7OII42EK6VBWAAKECW/events.json","paper":"https://pith.science/paper/3LLCW3RU"},"agent_actions":{"view_html":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW","download_json":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW.json","view_paper":"https://pith.science/paper/3LLCW3RU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.13095&json=true","fetch_graph":"https://pith.science/api/pith-number/3LLCW3RU7OII42EK6VBWAAKECW/graph.json","fetch_events":"https://pith.science/api/pith-number/3LLCW3RU7OII42EK6VBWAAKECW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW/action/storage_attestation","attest_author":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW/action/author_attestation","sign_citation":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW/action/citation_signature","submit_replication":"https://pith.science/pith/3LLCW3RU7OII42EK6VBWAAKECW/action/replication_record"}},"created_at":"2026-06-12T01:09:39.891198+00:00","updated_at":"2026-06-12T01:09:39.891198+00:00"}