{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AHXH2G7J6BFJXQCQLLXGJWJ5VT","short_pith_number":"pith:AHXH2G7J","schema_version":"1.0","canonical_sha256":"01ee7d1be9f04a9bc0505aee64d93dacf0e4838ddea5136c4bcaedb37f35dc35","source":{"kind":"arxiv","id":"2409.08596","version":2},"attestation_state":"computed","paper":{"title":"Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Helen Meng, Jiawen Kang, Lingwei Meng, Shujie Hu, Wenxuan Wu, Xixin Wu, Xunying Liu, Yuejiao Wang, Zhaoqing Li","submitted_at":"2024-09-13T07:28:28Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker scenarios. In this work, we present a pioneering effort to investigate the capability of LLMs in transcribing speech in multi-talker environments, following versatile instructions related to multi-talker automatic speech recognition (ASR), target talker ASR, and ASR based on specific talker attributes such as sex, occurrence order, language, and keyword spo"},"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":"2409.08596","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T07:28:28Z","cross_cats_sorted":["cs.AI","cs.SD","eess.AS"],"title_canon_sha256":"2918f42bf05debcd9f038e79d500eb0659d9ecf1822c2c645325b13112a3bbeb","abstract_canon_sha256":"9e3b456fb20b0e06c2ee75415c4954edf7bfcd1a8642fdb2b95bc3f25ac2f67d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:25.422307Z","signature_b64":"Cekhd4UO3LlqUXGwA2V34oSecekTW3t+Cq6uxpFKdO++h8kutwPf45QNymesdY2hpTV5jpmmm7VuEaAxDWORBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01ee7d1be9f04a9bc0505aee64d93dacf0e4838ddea5136c4bcaedb37f35dc35","last_reissued_at":"2026-07-05T10:43:25.421809Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:25.421809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Helen Meng, Jiawen Kang, Lingwei Meng, Shujie Hu, Wenxuan Wu, Xixin Wu, Xunying Liu, Yuejiao Wang, Zhaoqing Li","submitted_at":"2024-09-13T07:28:28Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker scenarios. In this work, we present a pioneering effort to investigate the capability of LLMs in transcribing speech in multi-talker environments, following versatile instructions related to multi-talker automatic speech recognition (ASR), target talker ASR, and ASR based on specific talker attributes such as sex, occurrence order, language, and keyword spo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08596","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/2409.08596/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":"2409.08596","created_at":"2026-07-05T10:43:25.421869+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08596v2","created_at":"2026-07-05T10:43:25.421869+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08596","created_at":"2026-07-05T10:43:25.421869+00:00"},{"alias_kind":"pith_short_12","alias_value":"AHXH2G7J6BFJ","created_at":"2026-07-05T10:43:25.421869+00:00"},{"alias_kind":"pith_short_16","alias_value":"AHXH2G7J6BFJXQCQ","created_at":"2026-07-05T10:43:25.421869+00:00"},{"alias_kind":"pith_short_8","alias_value":"AHXH2G7J","created_at":"2026-07-05T10:43:25.421869+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.22646","citing_title":"Speaker Targeting via Self-Speaker Adaptation for Multi-talker ASR","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AHXH2G7J6BFJXQCQLLXGJWJ5VT","json":"https://pith.science/pith/AHXH2G7J6BFJXQCQLLXGJWJ5VT.json","graph_json":"https://pith.science/api/pith-number/AHXH2G7J6BFJXQCQLLXGJWJ5VT/graph.json","events_json":"https://pith.science/api/pith-number/AHXH2G7J6BFJXQCQLLXGJWJ5VT/events.json","paper":"https://pith.science/paper/AHXH2G7J"},"agent_actions":{"view_html":"https://pith.science/pith/AHXH2G7J6BFJXQCQLLXGJWJ5VT","download_json":"https://pith.science/pith/AHXH2G7J6BFJXQCQLLXGJWJ5VT.json","view_paper":"https://pith.science/paper/AHXH2G7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08596&json=true","fetch_graph":"https://pith.science/api/pith-number/AHXH2G7J6BFJXQCQLLXGJWJ5VT/graph.json","fetch_events":"https://pith.science/api/pith-number/AHXH2G7J6BFJXQCQLLXGJWJ5VT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AHXH2G7J6BFJXQCQLLXGJWJ5VT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AHXH2G7J6BFJXQCQLLXGJWJ5VT/action/storage_attestation","attest_author":"https://pith.science/pith/AHXH2G7J6BFJXQCQLLXGJWJ5VT/action/author_attestation","sign_citation":"https://pith.science/pith/AHXH2G7J6BFJXQCQLLXGJWJ5VT/action/citation_signature","submit_replication":"https://pith.science/pith/AHXH2G7J6BFJXQCQLLXGJWJ5VT/action/replication_record"}},"created_at":"2026-07-05T10:43:25.421869+00:00","updated_at":"2026-07-05T10:43:25.421869+00:00"}