{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:VTGAZ5P7QLXY4NV4DUIWGDBH63","short_pith_number":"pith:VTGAZ5P7","schema_version":"1.0","canonical_sha256":"accc0cf5ff82ef8e36bc1d11630c27f6cac9bc6892bc7293e7b4966f8962d461","source":{"kind":"arxiv","id":"1710.11439","version":4},"attestation_state":"computed","paper":{"title":"Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Katsutoshi Itoyama, Kazuyoshi Yoshii, Masato Mimura, Tatsuya Kawahara, Yoshiaki Bando","submitted_at":"2017-10-31T12:52:09Z","abstract_excerpt":"This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervised approach requires a very large amount of pair data for training, it is not robust against unknown environments. Another approach is to use non-negative matrix factorization (NMF) based on basis spectra trained on clean speech in advance and those adapted to noise on the fly. T"},"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":"1710.11439","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2017-10-31T12:52:09Z","cross_cats_sorted":["cs.LG","eess.AS","stat.ML"],"title_canon_sha256":"a577a1eef2efcec72a9778e892fe63ad8082a0d2cde3ae2f1892689dc5b9e5bb","abstract_canon_sha256":"4d0ca808096c711856acba8b109bc33e746f1acb3d282d197cf6f99407f55bc9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:44.440331Z","signature_b64":"sY4ZNZMLD/6gDR8iXQNGesM3E7GJAEwUUIcZyLblxlQgTiuN5PPFTokriKyqX5eLk8oHATI4fisYTxWGs7sCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"accc0cf5ff82ef8e36bc1d11630c27f6cac9bc6892bc7293e7b4966f8962d461","last_reissued_at":"2026-05-17T23:51:44.439783Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:44.439783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Statistical Speech Enhancement Based on Probabilistic Integration of Variational Autoencoder and Non-Negative Matrix Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS","stat.ML"],"primary_cat":"cs.SD","authors_text":"Katsutoshi Itoyama, Kazuyoshi Yoshii, Masato Mimura, Tatsuya Kawahara, Yoshiaki Bando","submitted_at":"2017-10-31T12:52:09Z","abstract_excerpt":"This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network (DNN) to take noisy speech as input and output clean speech. Although this supervised approach requires a very large amount of pair data for training, it is not robust against unknown environments. Another approach is to use non-negative matrix factorization (NMF) based on basis spectra trained on clean speech in advance and those adapted to noise on the fly. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11439","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1710.11439","created_at":"2026-05-17T23:51:44.439867+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.11439v4","created_at":"2026-05-17T23:51:44.439867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11439","created_at":"2026-05-17T23:51:44.439867+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTGAZ5P7QLXY","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTGAZ5P7QLXY4NV4","created_at":"2026-05-18T12:31:49.984773+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTGAZ5P7","created_at":"2026-05-18T12:31:49.984773+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/VTGAZ5P7QLXY4NV4DUIWGDBH63","json":"https://pith.science/pith/VTGAZ5P7QLXY4NV4DUIWGDBH63.json","graph_json":"https://pith.science/api/pith-number/VTGAZ5P7QLXY4NV4DUIWGDBH63/graph.json","events_json":"https://pith.science/api/pith-number/VTGAZ5P7QLXY4NV4DUIWGDBH63/events.json","paper":"https://pith.science/paper/VTGAZ5P7"},"agent_actions":{"view_html":"https://pith.science/pith/VTGAZ5P7QLXY4NV4DUIWGDBH63","download_json":"https://pith.science/pith/VTGAZ5P7QLXY4NV4DUIWGDBH63.json","view_paper":"https://pith.science/paper/VTGAZ5P7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.11439&json=true","fetch_graph":"https://pith.science/api/pith-number/VTGAZ5P7QLXY4NV4DUIWGDBH63/graph.json","fetch_events":"https://pith.science/api/pith-number/VTGAZ5P7QLXY4NV4DUIWGDBH63/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTGAZ5P7QLXY4NV4DUIWGDBH63/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTGAZ5P7QLXY4NV4DUIWGDBH63/action/storage_attestation","attest_author":"https://pith.science/pith/VTGAZ5P7QLXY4NV4DUIWGDBH63/action/author_attestation","sign_citation":"https://pith.science/pith/VTGAZ5P7QLXY4NV4DUIWGDBH63/action/citation_signature","submit_replication":"https://pith.science/pith/VTGAZ5P7QLXY4NV4DUIWGDBH63/action/replication_record"}},"created_at":"2026-05-17T23:51:44.439867+00:00","updated_at":"2026-05-17T23:51:44.439867+00:00"}