{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PKU6P56FX775MRKTGZEZKOJLQQ","short_pith_number":"pith:PKU6P56F","schema_version":"1.0","canonical_sha256":"7aa9e7f7c5bfffd64553364995392b843d862b189f4808a81cfd3a17a5e4ef38","source":{"kind":"arxiv","id":"2601.06896","version":2},"attestation_state":"computed","paper":{"title":"TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Mingyue Huo, Yiwen Shao, Yuheng Zhang","submitted_at":"2026-01-11T12:40:07Z","abstract_excerpt":"We present TagSpeech, a unified LLM-based framework that utilizes Temporal Anchor Grounding for joint multi-speaker ASR and diarization. The framework is built on two key designs: (1) decoupled semantic and speaker streams fine-tuned via Serialized Output Training (SOT) to learn turn-taking dynamics; and (2) an interleaved time anchor mechanism that not only supports fine-grained timestamp prediction but also acts as a synchronization signal between semantic understanding and speaker tracking. Compared to previous works that primarily focus on speaker-attributed ASR or implicit diarization, Ta"},"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":"2601.06896","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-01-11T12:40:07Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0790bf920deac84ddc0b9d6c87fb5ea3eeda7aca5599907d2760cadeb022fd9d","abstract_canon_sha256":"4a644c02226aa732f8e30331cbbbcd6d130346ca31033e7d945d762a8ce6a7f7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:22:03.161398Z","signature_b64":"8MPKleGUrnKN5OE0YQHMPga9XboxecxnhSQ3vlh9Z6A7fy5U8JOK5MP/ebZ/HP/RG8NUvmJOyirg5hL2b+t1Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7aa9e7f7c5bfffd64553364995392b843d862b189f4808a81cfd3a17a5e4ef38","last_reissued_at":"2026-07-14T01:22:03.160431Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:22:03.160431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Mingyue Huo, Yiwen Shao, Yuheng Zhang","submitted_at":"2026-01-11T12:40:07Z","abstract_excerpt":"We present TagSpeech, a unified LLM-based framework that utilizes Temporal Anchor Grounding for joint multi-speaker ASR and diarization. The framework is built on two key designs: (1) decoupled semantic and speaker streams fine-tuned via Serialized Output Training (SOT) to learn turn-taking dynamics; and (2) an interleaved time anchor mechanism that not only supports fine-grained timestamp prediction but also acts as a synchronization signal between semantic understanding and speaker tracking. Compared to previous works that primarily focus on speaker-attributed ASR or implicit diarization, Ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.06896","kind":"arxiv","version":2},"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/2601.06896/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":"2601.06896","created_at":"2026-07-14T01:22:03.160867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.06896v2","created_at":"2026-07-14T01:22:03.160867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.06896","created_at":"2026-07-14T01:22:03.160867+00:00"},{"alias_kind":"pith_short_12","alias_value":"PKU6P56FX775","created_at":"2026-07-14T01:22:03.160867+00:00"},{"alias_kind":"pith_short_16","alias_value":"PKU6P56FX775MRKT","created_at":"2026-07-14T01:22:03.160867+00:00"},{"alias_kind":"pith_short_8","alias_value":"PKU6P56F","created_at":"2026-07-14T01:22:03.160867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2606.22868","citing_title":"MSU-Bench: Towards Speaker-Centric Understanding in Conversational Multi-Speaker Scenarios","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13095","citing_title":"Balancing ASR and diarization in end-to-end LLMs for multi-talker speech recognition","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.02400","citing_title":"SoulX-Transcriber: A Robust End-to-End Framework for Multi-Speaker Speech Transcription","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03074","citing_title":"Speaker-Reasoner: Scaling Interaction Turns and Reasoning Patterns for Timestamped Speaker-Attributed ASR","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22245","citing_title":"Listening with Time: Precise Temporal Awareness for Long-Form Audio Understanding","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22467","citing_title":"DM-ASR: Diarization-aware Multi-speaker ASR with Large Language Models","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PKU6P56FX775MRKTGZEZKOJLQQ","json":"https://pith.science/pith/PKU6P56FX775MRKTGZEZKOJLQQ.json","graph_json":"https://pith.science/api/pith-number/PKU6P56FX775MRKTGZEZKOJLQQ/graph.json","events_json":"https://pith.science/api/pith-number/PKU6P56FX775MRKTGZEZKOJLQQ/events.json","paper":"https://pith.science/paper/PKU6P56F"},"agent_actions":{"view_html":"https://pith.science/pith/PKU6P56FX775MRKTGZEZKOJLQQ","download_json":"https://pith.science/pith/PKU6P56FX775MRKTGZEZKOJLQQ.json","view_paper":"https://pith.science/paper/PKU6P56F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.06896&json=true","fetch_graph":"https://pith.science/api/pith-number/PKU6P56FX775MRKTGZEZKOJLQQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PKU6P56FX775MRKTGZEZKOJLQQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PKU6P56FX775MRKTGZEZKOJLQQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PKU6P56FX775MRKTGZEZKOJLQQ/action/storage_attestation","attest_author":"https://pith.science/pith/PKU6P56FX775MRKTGZEZKOJLQQ/action/author_attestation","sign_citation":"https://pith.science/pith/PKU6P56FX775MRKTGZEZKOJLQQ/action/citation_signature","submit_replication":"https://pith.science/pith/PKU6P56FX775MRKTGZEZKOJLQQ/action/replication_record"}},"created_at":"2026-07-14T01:22:03.160867+00:00","updated_at":"2026-07-14T01:22:03.160867+00:00"}