{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IKOFMHN6FLFGDR7TT5XI7RDHA5","short_pith_number":"pith:IKOFMHN6","schema_version":"1.0","canonical_sha256":"429c561dbe2aca61c7f39f6e8fc4670742a93e4423aa30085bbe3a49282d487b","source":{"kind":"arxiv","id":"2403.10271","version":3},"attestation_state":"computed","paper":{"title":"SuperM2M: Supervised and Mixture-to-Mixture Co-Learning for Speech Enhancement and Noise-Robust ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"eess.AS","authors_text":"Zhong-Qiu Wang","submitted_at":"2024-03-15T13:03:24Z","abstract_excerpt":"The current dominant approach for neural speech enhancement is based on supervised learning by using simulated training data. The trained models, however, often exhibit limited generalizability to real-recorded data. To address this, this paper investigates training enhancement models directly on real target-domain data. We propose to adapt mixture-to-mixture (M2M) training, originally designed for speaker separation, for speech enhancement, by modeling multi-source noise signals as a single, combined source. In addition, we propose a co-learning algorithm that improves M2M with the help of su"},"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":"2403.10271","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-03-15T13:03:24Z","cross_cats_sorted":["eess.SP"],"title_canon_sha256":"8048030a09eab142813ac5b325f82e1ea9c595227333f5bf64714cdb37388854","abstract_canon_sha256":"0ba34527cb5d73d0ad6c0f0521f452b4cc12e4ac11827e4d1b1a14a1d01f05dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:24.862209Z","signature_b64":"qNe4W0AbOUA12+ugfsS8W2/DmA14Fr+OWiCIz4VPEqugFuTbsCAy6pJVMW2sQmLO7QY2vtKlZW8wFKt+1SSEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"429c561dbe2aca61c7f39f6e8fc4670742a93e4423aa30085bbe3a49282d487b","last_reissued_at":"2026-07-05T10:37:24.861736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:24.861736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SuperM2M: Supervised and Mixture-to-Mixture Co-Learning for Speech Enhancement and Noise-Robust ASR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.SP"],"primary_cat":"eess.AS","authors_text":"Zhong-Qiu Wang","submitted_at":"2024-03-15T13:03:24Z","abstract_excerpt":"The current dominant approach for neural speech enhancement is based on supervised learning by using simulated training data. The trained models, however, often exhibit limited generalizability to real-recorded data. To address this, this paper investigates training enhancement models directly on real target-domain data. We propose to adapt mixture-to-mixture (M2M) training, originally designed for speaker separation, for speech enhancement, by modeling multi-source noise signals as a single, combined source. In addition, we propose a co-learning algorithm that improves M2M with the help of su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10271","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/2403.10271/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":"2403.10271","created_at":"2026-07-05T10:37:24.861792+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.10271v3","created_at":"2026-07-05T10:37:24.861792+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10271","created_at":"2026-07-05T10:37:24.861792+00:00"},{"alias_kind":"pith_short_12","alias_value":"IKOFMHN6FLFG","created_at":"2026-07-05T10:37:24.861792+00:00"},{"alias_kind":"pith_short_16","alias_value":"IKOFMHN6FLFGDR7T","created_at":"2026-07-05T10:37:24.861792+00:00"},{"alias_kind":"pith_short_8","alias_value":"IKOFMHN6","created_at":"2026-07-05T10:37:24.861792+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24450","citing_title":"SuPseudo: A Pseudo-supervised Learning Method for Neural Speech Enhancement in Far-field Speech Recognition","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IKOFMHN6FLFGDR7TT5XI7RDHA5","json":"https://pith.science/pith/IKOFMHN6FLFGDR7TT5XI7RDHA5.json","graph_json":"https://pith.science/api/pith-number/IKOFMHN6FLFGDR7TT5XI7RDHA5/graph.json","events_json":"https://pith.science/api/pith-number/IKOFMHN6FLFGDR7TT5XI7RDHA5/events.json","paper":"https://pith.science/paper/IKOFMHN6"},"agent_actions":{"view_html":"https://pith.science/pith/IKOFMHN6FLFGDR7TT5XI7RDHA5","download_json":"https://pith.science/pith/IKOFMHN6FLFGDR7TT5XI7RDHA5.json","view_paper":"https://pith.science/paper/IKOFMHN6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.10271&json=true","fetch_graph":"https://pith.science/api/pith-number/IKOFMHN6FLFGDR7TT5XI7RDHA5/graph.json","fetch_events":"https://pith.science/api/pith-number/IKOFMHN6FLFGDR7TT5XI7RDHA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IKOFMHN6FLFGDR7TT5XI7RDHA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IKOFMHN6FLFGDR7TT5XI7RDHA5/action/storage_attestation","attest_author":"https://pith.science/pith/IKOFMHN6FLFGDR7TT5XI7RDHA5/action/author_attestation","sign_citation":"https://pith.science/pith/IKOFMHN6FLFGDR7TT5XI7RDHA5/action/citation_signature","submit_replication":"https://pith.science/pith/IKOFMHN6FLFGDR7TT5XI7RDHA5/action/replication_record"}},"created_at":"2026-07-05T10:37:24.861792+00:00","updated_at":"2026-07-05T10:37:24.861792+00:00"}