{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NRHXSGFMVSTITE2R6GEO3BU3OH","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":"802798f2ff90e79f21c18380c9c4f3322e0d3fd9434ff3ba97f68f58add766eb","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-02T19:43:45Z","title_canon_sha256":"b736ae8b3dddf4c3d648c194239c52baf5c98ac304527cb7ffb4102a6110b63a"},"schema_version":"1.0","source":{"id":"2409.01438","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01438","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01438v2","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01438","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"NRHXSGFMVSTI","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"pith_short_16","alias_value":"NRHXSGFMVSTITE2R","created_at":"2026-07-05T09:43:32Z"},{"alias_kind":"pith_short_8","alias_value":"NRHXSGFM","created_at":"2026-07-05T09:43:32Z"}],"graph_snapshots":[{"event_id":"sha256:a5eee34e4357936fe17a4a6b6619199f3eb2846f31144927c7d722e51309ceac","target":"graph","created_at":"2026-07-05T09:43:32Z","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/2409.01438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Boris Ginsburg, He Huang, Ivan Medennikov, Jagadeesh Balam, Krishna C. Puvvada, Kunal Dhawan, Somshubra Majumdar, Taejin Park, Weiqing Wang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-02T19:43:45Z","title":"Resource-Efficient Adaptation of Speech Foundation Models for Multi-Speaker ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01438","kind":"arxiv","version":2},"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:d05e74aefb9c42105a8c39dbe8b5a05188540d72e036b1844833b6913e65936d","target":"record","created_at":"2026-07-05T09:43:32Z","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":"802798f2ff90e79f21c18380c9c4f3322e0d3fd9434ff3ba97f68f58add766eb","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-02T19:43:45Z","title_canon_sha256":"b736ae8b3dddf4c3d648c194239c52baf5c98ac304527cb7ffb4102a6110b63a"},"schema_version":"1.0","source":{"id":"2409.01438","kind":"arxiv","version":2}},"canonical_sha256":"6c4f7918acaca6899351f188ed869b71d8bc2d6d7f236a7975795b7e380e9b8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c4f7918acaca6899351f188ed869b71d8bc2d6d7f236a7975795b7e380e9b8f","first_computed_at":"2026-07-05T09:43:32.964855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:32.964855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a+AIKuJlIizaBwFT0DkZh/u2ZFmvYnks1TFlRxpkDqhkrPZDcxGgWjNnMCBFHQlFck0UF8yDF13VXMa2j1EgDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:32.965771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01438","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d05e74aefb9c42105a8c39dbe8b5a05188540d72e036b1844833b6913e65936d","sha256:a5eee34e4357936fe17a4a6b6619199f3eb2846f31144927c7d722e51309ceac"],"state_sha256":"60c246821a53032400fd29b3d82b96e0624968f5f3eb08563acbe8114db21809"}