{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A6EMJP32Y7SLWSYVV3X6PIWOOI","short_pith_number":"pith:A6EMJP32","schema_version":"1.0","canonical_sha256":"0788c4bf7ac7e4bb4b15aeefe7a2ce723016cc5cbc9cccbaaa9c2f06d4ca3332","source":{"kind":"arxiv","id":"2402.13511","version":2},"attestation_state":"computed","paper":{"title":"Mel-FullSubNet: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Rui Zhou, Xian Li, Xiaofei Li, Ying Fang","submitted_at":"2024-02-21T03:48:53Z","abstract_excerpt":"In this work, we propose Mel-FullSubNet, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance. Mel-FullSubNet takes as input the noisy and reverberant Mel-spectrogram and predicts the corresponding clean Mel-spectrogram. The enhanced Mel-spectrogram can be either transformed to speech waveform with a neural vocoder or directly used for ASR. Mel-FullSubNet encapsulates interleaved full-band and sub-band networks, for learning the full-band spectral pattern of signals and the sub-band/narrow-ba"},"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":"2402.13511","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-02-21T03:48:53Z","cross_cats_sorted":[],"title_canon_sha256":"2c3d0d7cea9c344135f7507585ea098e336b64f0ee9c370b5d8de5e79699e02b","abstract_canon_sha256":"54e3c76de54a30c1b51094baf0e3ccbdb9194e41be58802537b8a1bdc279d650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:48:04.350131Z","signature_b64":"iWStsTvkAbdxOOZaC4uiLd20e05Jgnd9lM0HZLJLFPpwzh0t2NElsHvQphXM++NvELdeLhlzxe5Kkbnj83iqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0788c4bf7ac7e4bb4b15aeefe7a2ce723016cc5cbc9cccbaaa9c2f06d4ca3332","last_reissued_at":"2026-07-05T07:48:04.349595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:48:04.349595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mel-FullSubNet: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Rui Zhou, Xian Li, Xiaofei Li, Ying Fang","submitted_at":"2024-02-21T03:48:53Z","abstract_excerpt":"In this work, we propose Mel-FullSubNet, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance. Mel-FullSubNet takes as input the noisy and reverberant Mel-spectrogram and predicts the corresponding clean Mel-spectrogram. The enhanced Mel-spectrogram can be either transformed to speech waveform with a neural vocoder or directly used for ASR. Mel-FullSubNet encapsulates interleaved full-band and sub-band networks, for learning the full-band spectral pattern of signals and the sub-band/narrow-ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13511","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/2402.13511/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":"2402.13511","created_at":"2026-07-05T07:48:04.349665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.13511v2","created_at":"2026-07-05T07:48:04.349665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13511","created_at":"2026-07-05T07:48:04.349665+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6EMJP32Y7SL","created_at":"2026-07-05T07:48:04.349665+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6EMJP32Y7SLWSYV","created_at":"2026-07-05T07:48:04.349665+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6EMJP32","created_at":"2026-07-05T07:48:04.349665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20731","citing_title":"Learning Neural Vocoder from Range-Null Space Decomposition","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A6EMJP32Y7SLWSYVV3X6PIWOOI","json":"https://pith.science/pith/A6EMJP32Y7SLWSYVV3X6PIWOOI.json","graph_json":"https://pith.science/api/pith-number/A6EMJP32Y7SLWSYVV3X6PIWOOI/graph.json","events_json":"https://pith.science/api/pith-number/A6EMJP32Y7SLWSYVV3X6PIWOOI/events.json","paper":"https://pith.science/paper/A6EMJP32"},"agent_actions":{"view_html":"https://pith.science/pith/A6EMJP32Y7SLWSYVV3X6PIWOOI","download_json":"https://pith.science/pith/A6EMJP32Y7SLWSYVV3X6PIWOOI.json","view_paper":"https://pith.science/paper/A6EMJP32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.13511&json=true","fetch_graph":"https://pith.science/api/pith-number/A6EMJP32Y7SLWSYVV3X6PIWOOI/graph.json","fetch_events":"https://pith.science/api/pith-number/A6EMJP32Y7SLWSYVV3X6PIWOOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6EMJP32Y7SLWSYVV3X6PIWOOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6EMJP32Y7SLWSYVV3X6PIWOOI/action/storage_attestation","attest_author":"https://pith.science/pith/A6EMJP32Y7SLWSYVV3X6PIWOOI/action/author_attestation","sign_citation":"https://pith.science/pith/A6EMJP32Y7SLWSYVV3X6PIWOOI/action/citation_signature","submit_replication":"https://pith.science/pith/A6EMJP32Y7SLWSYVV3X6PIWOOI/action/replication_record"}},"created_at":"2026-07-05T07:48:04.349665+00:00","updated_at":"2026-07-05T07:48:04.349665+00:00"}