{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LALH7HIOHG4HHAUE5CK3KO5K5U","short_pith_number":"pith:LALH7HIO","schema_version":"1.0","canonical_sha256":"58167f9d0e39b8738284e895b53baaed109c88a680a62194e26b84bc050add07","source":{"kind":"arxiv","id":"2409.11889","version":3},"attestation_state":"computed","paper":{"title":"M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Aobo Kong, Haoqin Sun, Hui Wang, Jiabei He, Jiaming Zhou, Shiwan Zhao, Wenjia Zeng, Yong Chen, Yong Qin","submitted_at":"2024-09-18T11:35:55Z","abstract_excerpt":"State-of-the-art models like OpenAI's Whisper exhibit strong performance in multilingual automatic speech recognition (ASR), but they still face challenges in accurately recognizing diverse subdialects. In this paper, we propose M2R-whisper, a novel multi-stage and multi-scale retrieval augmentation approach designed to enhance ASR performance in low-resource settings. Building on the principles of in-context learning (ICL) and retrieval-augmented techniques, our method employs sentence-level ICL in the pre-processing stage to harness contextual information, while integrating token-level k-Nea"},"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":"2409.11889","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-18T11:35:55Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"f946424b14847f9e8275b98fd821b29e0389ea96ce97145bd4964ed4adde53fb","abstract_canon_sha256":"c7a07b2d5a4038c11fef1cd7460e737bd2512d5b45ddc2c10c9e0112c6fd17da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:23.331338Z","signature_b64":"vXMKul3uWxe68OoRkRg96thdiQ9V4+0Zsewl8CVBwPfT5uOXKQZpC77AxmhwN22TvbtJSoR1IH6U6eoCgS3uDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58167f9d0e39b8738284e895b53baaed109c88a680a62194e26b84bc050add07","last_reissued_at":"2026-07-05T10:29:23.330628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:23.330628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"M2R-Whisper: Multi-stage and Multi-scale Retrieval Augmentation for Enhancing Whisper","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Aobo Kong, Haoqin Sun, Hui Wang, Jiabei He, Jiaming Zhou, Shiwan Zhao, Wenjia Zeng, Yong Chen, Yong Qin","submitted_at":"2024-09-18T11:35:55Z","abstract_excerpt":"State-of-the-art models like OpenAI's Whisper exhibit strong performance in multilingual automatic speech recognition (ASR), but they still face challenges in accurately recognizing diverse subdialects. In this paper, we propose M2R-whisper, a novel multi-stage and multi-scale retrieval augmentation approach designed to enhance ASR performance in low-resource settings. Building on the principles of in-context learning (ICL) and retrieval-augmented techniques, our method employs sentence-level ICL in the pre-processing stage to harness contextual information, while integrating token-level k-Nea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11889","kind":"arxiv","version":3},"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/2409.11889/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":"2409.11889","created_at":"2026-07-05T10:29:23.330703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11889v3","created_at":"2026-07-05T10:29:23.330703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11889","created_at":"2026-07-05T10:29:23.330703+00:00"},{"alias_kind":"pith_short_12","alias_value":"LALH7HIOHG4H","created_at":"2026-07-05T10:29:23.330703+00:00"},{"alias_kind":"pith_short_16","alias_value":"LALH7HIOHG4HHAUE","created_at":"2026-07-05T10:29:23.330703+00:00"},{"alias_kind":"pith_short_8","alias_value":"LALH7HIO","created_at":"2026-07-05T10:29:23.330703+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/LALH7HIOHG4HHAUE5CK3KO5K5U","json":"https://pith.science/pith/LALH7HIOHG4HHAUE5CK3KO5K5U.json","graph_json":"https://pith.science/api/pith-number/LALH7HIOHG4HHAUE5CK3KO5K5U/graph.json","events_json":"https://pith.science/api/pith-number/LALH7HIOHG4HHAUE5CK3KO5K5U/events.json","paper":"https://pith.science/paper/LALH7HIO"},"agent_actions":{"view_html":"https://pith.science/pith/LALH7HIOHG4HHAUE5CK3KO5K5U","download_json":"https://pith.science/pith/LALH7HIOHG4HHAUE5CK3KO5K5U.json","view_paper":"https://pith.science/paper/LALH7HIO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11889&json=true","fetch_graph":"https://pith.science/api/pith-number/LALH7HIOHG4HHAUE5CK3KO5K5U/graph.json","fetch_events":"https://pith.science/api/pith-number/LALH7HIOHG4HHAUE5CK3KO5K5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LALH7HIOHG4HHAUE5CK3KO5K5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LALH7HIOHG4HHAUE5CK3KO5K5U/action/storage_attestation","attest_author":"https://pith.science/pith/LALH7HIOHG4HHAUE5CK3KO5K5U/action/author_attestation","sign_citation":"https://pith.science/pith/LALH7HIOHG4HHAUE5CK3KO5K5U/action/citation_signature","submit_replication":"https://pith.science/pith/LALH7HIOHG4HHAUE5CK3KO5K5U/action/replication_record"}},"created_at":"2026-07-05T10:29:23.330703+00:00","updated_at":"2026-07-05T10:29:23.330703+00:00"}