{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NRHXSGFMVSTITE2R6GEO3BU3OH","short_pith_number":"pith:NRHXSGFM","schema_version":"1.0","canonical_sha256":"6c4f7918acaca6899351f188ed869b71d8bc2d6d7f236a7975795b7e380e9b8f","source":{"kind":"arxiv","id":"2409.01438","version":2},"attestation_state":"computed","paper":{"title":"Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, He Huang, Ivan Medennikov, Jagadeesh Balam, Krishna C. Puvvada, Kunal Dhawan, Somshubra Majumdar, Taejin Park, Weiqing Wang","submitted_at":"2024-09-02T19:43:45Z","abstract_excerpt":"Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi-speaker ASR remains a challenging task for these models due to data scarcity and sparsity. In this paper, we present approaches to enable speech foundation models to process and understand multi-speaker speech with limited training data. Specifically, we adapt a speech foundation model for the multi-speaker ASR task using only telephonic data. Remarkably, the adapted model also performs well on meeting data without "},"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":"2409.01438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-02T19:43:45Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"b736ae8b3dddf4c3d648c194239c52baf5c98ac304527cb7ffb4102a6110b63a","abstract_canon_sha256":"802798f2ff90e79f21c18380c9c4f3322e0d3fd9434ff3ba97f68f58add766eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:32.965771Z","signature_b64":"a+AIKuJlIizaBwFT0DkZh/u2ZFmvYnks1TFlRxpkDqhkrPZDcxGgWjNnMCBFHQlFck0UF8yDF13VXMa2j1EgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c4f7918acaca6899351f188ed869b71d8bc2d6d7f236a7975795b7e380e9b8f","last_reissued_at":"2026-07-05T09:43:32.964855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:32.964855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Boris Ginsburg, He Huang, Ivan Medennikov, Jagadeesh Balam, Krishna C. Puvvada, Kunal Dhawan, Somshubra Majumdar, Taejin Park, Weiqing Wang","submitted_at":"2024-09-02T19:43:45Z","abstract_excerpt":"Speech foundation models have achieved state-of-the-art (SoTA) performance across various tasks, such as automatic speech recognition (ASR) in hundreds of languages. However, multi-speaker ASR remains a challenging task for these models due to data scarcity and sparsity. In this paper, we present approaches to enable speech foundation models to process and understand multi-speaker speech with limited training data. Specifically, we adapt a speech foundation model for the multi-speaker ASR task using only telephonic data. Remarkably, the adapted model also performs well on meeting data without "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01438","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/2409.01438/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":"2409.01438","created_at":"2026-07-05T09:43:32.964958+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01438v2","created_at":"2026-07-05T09:43:32.964958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01438","created_at":"2026-07-05T09:43:32.964958+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRHXSGFMVSTI","created_at":"2026-07-05T09:43:32.964958+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRHXSGFMVSTITE2R","created_at":"2026-07-05T09:43:32.964958+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRHXSGFM","created_at":"2026-07-05T09:43:32.964958+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/NRHXSGFMVSTITE2R6GEO3BU3OH","json":"https://pith.science/pith/NRHXSGFMVSTITE2R6GEO3BU3OH.json","graph_json":"https://pith.science/api/pith-number/NRHXSGFMVSTITE2R6GEO3BU3OH/graph.json","events_json":"https://pith.science/api/pith-number/NRHXSGFMVSTITE2R6GEO3BU3OH/events.json","paper":"https://pith.science/paper/NRHXSGFM"},"agent_actions":{"view_html":"https://pith.science/pith/NRHXSGFMVSTITE2R6GEO3BU3OH","download_json":"https://pith.science/pith/NRHXSGFMVSTITE2R6GEO3BU3OH.json","view_paper":"https://pith.science/paper/NRHXSGFM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01438&json=true","fetch_graph":"https://pith.science/api/pith-number/NRHXSGFMVSTITE2R6GEO3BU3OH/graph.json","fetch_events":"https://pith.science/api/pith-number/NRHXSGFMVSTITE2R6GEO3BU3OH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRHXSGFMVSTITE2R6GEO3BU3OH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRHXSGFMVSTITE2R6GEO3BU3OH/action/storage_attestation","attest_author":"https://pith.science/pith/NRHXSGFMVSTITE2R6GEO3BU3OH/action/author_attestation","sign_citation":"https://pith.science/pith/NRHXSGFMVSTITE2R6GEO3BU3OH/action/citation_signature","submit_replication":"https://pith.science/pith/NRHXSGFMVSTITE2R6GEO3BU3OH/action/replication_record"}},"created_at":"2026-07-05T09:43:32.964958+00:00","updated_at":"2026-07-05T09:43:32.964958+00:00"}