{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6FBXVOQYKFQUVLLPUR6WRCYZ7R","short_pith_number":"pith:6FBXVOQY","schema_version":"1.0","canonical_sha256":"f1437aba1851614aad6fa47d688b19fc5bca30491ed2e21e3496d69c620f8a8f","source":{"kind":"arxiv","id":"1811.02480","version":3},"attestation_state":"computed","paper":{"title":"Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Giovanni Morrone, Leonardo Badino, Luca Pasa, Luciano Fadiga, Sonia Bergamaschi, Vadim Tikhanoff","submitted_at":"2018-11-06T16:35:01Z","abstract_excerpt":"In this paper, we address the problem of enhancing the speech of a speaker of interest in a cocktail party scenario when visual information of the speaker of interest is available. Contrary to most previous studies, we do not learn visual features on the typically small audio-visual datasets, but use an already available face landmark detector (trained on a separate image dataset). The landmarks are used by LSTM-based models to generate time-frequency masks which are applied to the acoustic mixed-speech spectrogram. Results show that: (i) landmark motion features are very effective features fo"},"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":"1811.02480","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-06T16:35:01Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"81b01ae61a9d81f8c32b44f44cab393ad3961e32608bbacfd1c57580b815b1dd","abstract_canon_sha256":"603fc71497b5d6bcf0fa597da0bff179c975111d71a8872d36ca1751683d3662"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:27.797894Z","signature_b64":"Rohr8LWh13+TCg6Szj2zg2mhgvuGpmHO01/67Z0y0r/yOxxYMjTi3Pykbn3ynh4m6xeh/yXoTxyQ4U9MWrhtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1437aba1851614aad6fa47d688b19fc5bca30491ed2e21e3496d69c620f8a8f","last_reissued_at":"2026-07-05T02:12:27.797282Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:27.797282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Giovanni Morrone, Leonardo Badino, Luca Pasa, Luciano Fadiga, Sonia Bergamaschi, Vadim Tikhanoff","submitted_at":"2018-11-06T16:35:01Z","abstract_excerpt":"In this paper, we address the problem of enhancing the speech of a speaker of interest in a cocktail party scenario when visual information of the speaker of interest is available. Contrary to most previous studies, we do not learn visual features on the typically small audio-visual datasets, but use an already available face landmark detector (trained on a separate image dataset). The landmarks are used by LSTM-based models to generate time-frequency masks which are applied to the acoustic mixed-speech spectrogram. Results show that: (i) landmark motion features are very effective features fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.02480","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/1811.02480/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":"1811.02480","created_at":"2026-07-05T02:12:27.797371+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.02480v3","created_at":"2026-07-05T02:12:27.797371+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.02480","created_at":"2026-07-05T02:12:27.797371+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FBXVOQYKFQU","created_at":"2026-07-05T02:12:27.797371+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FBXVOQYKFQUVLLP","created_at":"2026-07-05T02:12:27.797371+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FBXVOQY","created_at":"2026-07-05T02:12:27.797371+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/6FBXVOQYKFQUVLLPUR6WRCYZ7R","json":"https://pith.science/pith/6FBXVOQYKFQUVLLPUR6WRCYZ7R.json","graph_json":"https://pith.science/api/pith-number/6FBXVOQYKFQUVLLPUR6WRCYZ7R/graph.json","events_json":"https://pith.science/api/pith-number/6FBXVOQYKFQUVLLPUR6WRCYZ7R/events.json","paper":"https://pith.science/paper/6FBXVOQY"},"agent_actions":{"view_html":"https://pith.science/pith/6FBXVOQYKFQUVLLPUR6WRCYZ7R","download_json":"https://pith.science/pith/6FBXVOQYKFQUVLLPUR6WRCYZ7R.json","view_paper":"https://pith.science/paper/6FBXVOQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.02480&json=true","fetch_graph":"https://pith.science/api/pith-number/6FBXVOQYKFQUVLLPUR6WRCYZ7R/graph.json","fetch_events":"https://pith.science/api/pith-number/6FBXVOQYKFQUVLLPUR6WRCYZ7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FBXVOQYKFQUVLLPUR6WRCYZ7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FBXVOQYKFQUVLLPUR6WRCYZ7R/action/storage_attestation","attest_author":"https://pith.science/pith/6FBXVOQYKFQUVLLPUR6WRCYZ7R/action/author_attestation","sign_citation":"https://pith.science/pith/6FBXVOQYKFQUVLLPUR6WRCYZ7R/action/citation_signature","submit_replication":"https://pith.science/pith/6FBXVOQYKFQUVLLPUR6WRCYZ7R/action/replication_record"}},"created_at":"2026-07-05T02:12:27.797371+00:00","updated_at":"2026-07-05T02:12:27.797371+00:00"}