{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6DAUNK5ARPCZA242B3Z3EJD5K5","short_pith_number":"pith:6DAUNK5A","schema_version":"1.0","canonical_sha256":"f0c146aba08bc5906b9a0ef3b2247d574aab32bf7cfeb656540ddde67e6be4d5","source":{"kind":"arxiv","id":"2106.12271","version":3},"attestation_state":"computed","paper":{"title":"Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Laurent Girin, Simon Leglaive, Xavier Alameda-Pineda, Xiaoyu Bie","submitted_at":"2021-06-23T09:48:38Z","abstract_excerpt":"Dynamical variational autoencoders (DVAEs) are a class of deep generative models with latent variables, dedicated to model time series of high-dimensional data. DVAEs can be considered as extensions of the variational autoencoder (VAE) that include temporal dependencies between successive observed and/or latent vectors. Previous work has shown the interest of using DVAEs over the VAE for speech spectrograms modeling. Independently, the VAE has been successfully applied to speech enhancement in noise, in an unsupervised noise-agnostic set-up that requires neither noise samples nor noisy speech "},"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":"2106.12271","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2021-06-23T09:48:38Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"a7ddf5218e99a493dae8289f68d119075a4c25add076d0fc3079b6677fbcde42","abstract_canon_sha256":"7e3dfc8a1725cb3205aa5ab0e450378d5948450b2095479849786d43ed048038"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:23.146540Z","signature_b64":"7RKDthfYSfkx+Yq1Q5irwYm2gkn7G+0AkWb7moYJG2eCmJNRpk5Skuo0qBrceUo+5UddwcMzp18oNTT9PEfBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0c146aba08bc5906b9a0ef3b2247d574aab32bf7cfeb656540ddde67e6be4d5","last_reissued_at":"2026-07-05T05:02:23.146144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:23.146144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Laurent Girin, Simon Leglaive, Xavier Alameda-Pineda, Xiaoyu Bie","submitted_at":"2021-06-23T09:48:38Z","abstract_excerpt":"Dynamical variational autoencoders (DVAEs) are a class of deep generative models with latent variables, dedicated to model time series of high-dimensional data. DVAEs can be considered as extensions of the variational autoencoder (VAE) that include temporal dependencies between successive observed and/or latent vectors. Previous work has shown the interest of using DVAEs over the VAE for speech spectrograms modeling. Independently, the VAE has been successfully applied to speech enhancement in noise, in an unsupervised noise-agnostic set-up that requires neither noise samples nor noisy speech "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.12271","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/2106.12271/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":"2106.12271","created_at":"2026-07-05T05:02:23.146202+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.12271v3","created_at":"2026-07-05T05:02:23.146202+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.12271","created_at":"2026-07-05T05:02:23.146202+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DAUNK5ARPCZ","created_at":"2026-07-05T05:02:23.146202+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DAUNK5ARPCZA242","created_at":"2026-07-05T05:02:23.146202+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DAUNK5A","created_at":"2026-07-05T05:02:23.146202+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/6DAUNK5ARPCZA242B3Z3EJD5K5","json":"https://pith.science/pith/6DAUNK5ARPCZA242B3Z3EJD5K5.json","graph_json":"https://pith.science/api/pith-number/6DAUNK5ARPCZA242B3Z3EJD5K5/graph.json","events_json":"https://pith.science/api/pith-number/6DAUNK5ARPCZA242B3Z3EJD5K5/events.json","paper":"https://pith.science/paper/6DAUNK5A"},"agent_actions":{"view_html":"https://pith.science/pith/6DAUNK5ARPCZA242B3Z3EJD5K5","download_json":"https://pith.science/pith/6DAUNK5ARPCZA242B3Z3EJD5K5.json","view_paper":"https://pith.science/paper/6DAUNK5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.12271&json=true","fetch_graph":"https://pith.science/api/pith-number/6DAUNK5ARPCZA242B3Z3EJD5K5/graph.json","fetch_events":"https://pith.science/api/pith-number/6DAUNK5ARPCZA242B3Z3EJD5K5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DAUNK5ARPCZA242B3Z3EJD5K5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DAUNK5ARPCZA242B3Z3EJD5K5/action/storage_attestation","attest_author":"https://pith.science/pith/6DAUNK5ARPCZA242B3Z3EJD5K5/action/author_attestation","sign_citation":"https://pith.science/pith/6DAUNK5ARPCZA242B3Z3EJD5K5/action/citation_signature","submit_replication":"https://pith.science/pith/6DAUNK5ARPCZA242B3Z3EJD5K5/action/replication_record"}},"created_at":"2026-07-05T05:02:23.146202+00:00","updated_at":"2026-07-05T05:02:23.146202+00:00"}