{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P74XXDLTSNISP3MX3PPSISRFZQ","short_pith_number":"pith:P74XXDLT","schema_version":"1.0","canonical_sha256":"7ff97b8d73935127ed97dbdf244a25cc163b551bcec4bd8b2b16c13fbcae0ef3","source":{"kind":"arxiv","id":"2505.24450","version":2},"attestation_state":"computed","paper":{"title":"SuPseudo: A Pseudo-supervised Learning Method for Neural Speech Enhancement in Far-field Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lin Li, Longjie Luo, Qingyang Hong","submitted_at":"2025-05-30T10:36:32Z","abstract_excerpt":"Due to the lack of target speech annotations in real-recorded far-field conversational datasets, speech enhancement (SE) models are typically trained on simulated data. However, the trained models often perform poorly in real-world conditions, hindering their application in far-field speech recognition. To address the issue, we (a) propose direct sound estimation (DSE) to estimate the oracle direct sound of real-recorded data for SE; and (b) present a novel pseudo-supervised learning method, SuPseudo, which leverages DSE-estimates as pseudo-labels and enables SE models to directly learn from a"},"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":"2505.24450","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-30T10:36:32Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"0f717d4f6f01b8839b4e57f0c428ef2ffcdaff2eee5eb084ea311aaac67d8971","abstract_canon_sha256":"835045d73a17a5ab2912b2e3ccebd197c2d2371b39a9352dfe42c5f05a0f3e60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:45.327128Z","signature_b64":"7L3JRodlb7xRhQ6/tml8C6YS0BvL2q5nnrPKV19OGeWxEWwq8J/t8uZFAqkosMBb2dNsc+q4a1JYaHqFDAZtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ff97b8d73935127ed97dbdf244a25cc163b551bcec4bd8b2b16c13fbcae0ef3","last_reissued_at":"2026-07-05T11:25:45.326665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:45.326665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SuPseudo: A Pseudo-supervised Learning Method for Neural Speech Enhancement in Far-field Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Lin Li, Longjie Luo, Qingyang Hong","submitted_at":"2025-05-30T10:36:32Z","abstract_excerpt":"Due to the lack of target speech annotations in real-recorded far-field conversational datasets, speech enhancement (SE) models are typically trained on simulated data. However, the trained models often perform poorly in real-world conditions, hindering their application in far-field speech recognition. To address the issue, we (a) propose direct sound estimation (DSE) to estimate the oracle direct sound of real-recorded data for SE; and (b) present a novel pseudo-supervised learning method, SuPseudo, which leverages DSE-estimates as pseudo-labels and enables SE models to directly learn from a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24450","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/2505.24450/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":"2505.24450","created_at":"2026-07-05T11:25:45.326727+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24450v2","created_at":"2026-07-05T11:25:45.326727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24450","created_at":"2026-07-05T11:25:45.326727+00:00"},{"alias_kind":"pith_short_12","alias_value":"P74XXDLTSNIS","created_at":"2026-07-05T11:25:45.326727+00:00"},{"alias_kind":"pith_short_16","alias_value":"P74XXDLTSNISP3MX","created_at":"2026-07-05T11:25:45.326727+00:00"},{"alias_kind":"pith_short_8","alias_value":"P74XXDLT","created_at":"2026-07-05T11:25:45.326727+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":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P74XXDLTSNISP3MX3PPSISRFZQ","json":"https://pith.science/pith/P74XXDLTSNISP3MX3PPSISRFZQ.json","graph_json":"https://pith.science/api/pith-number/P74XXDLTSNISP3MX3PPSISRFZQ/graph.json","events_json":"https://pith.science/api/pith-number/P74XXDLTSNISP3MX3PPSISRFZQ/events.json","paper":"https://pith.science/paper/P74XXDLT"},"agent_actions":{"view_html":"https://pith.science/pith/P74XXDLTSNISP3MX3PPSISRFZQ","download_json":"https://pith.science/pith/P74XXDLTSNISP3MX3PPSISRFZQ.json","view_paper":"https://pith.science/paper/P74XXDLT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24450&json=true","fetch_graph":"https://pith.science/api/pith-number/P74XXDLTSNISP3MX3PPSISRFZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/P74XXDLTSNISP3MX3PPSISRFZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P74XXDLTSNISP3MX3PPSISRFZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P74XXDLTSNISP3MX3PPSISRFZQ/action/storage_attestation","attest_author":"https://pith.science/pith/P74XXDLTSNISP3MX3PPSISRFZQ/action/author_attestation","sign_citation":"https://pith.science/pith/P74XXDLTSNISP3MX3PPSISRFZQ/action/citation_signature","submit_replication":"https://pith.science/pith/P74XXDLTSNISP3MX3PPSISRFZQ/action/replication_record"}},"created_at":"2026-07-05T11:25:45.326727+00:00","updated_at":"2026-07-05T11:25:45.326727+00:00"}