{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:MV4RLBBEVDY6MN3CP5E5B36SDS","short_pith_number":"pith:MV4RLBBE","schema_version":"1.0","canonical_sha256":"6579158424a8f1e637627f49d0efd21cbcf6721150b379594bce335db6908ead","source":{"kind":"arxiv","id":"1707.02749","version":1},"attestation_state":"computed","paper":{"title":"Improving speaker turn embedding by crossmodal transfer learning from face embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jean-Marc Odobez, Nam Le","submitted_at":"2017-07-10T08:51:53Z","abstract_excerpt":"Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail. However, this improvement is relatively limited when compared to the gain observed in face embedding learning, which has been proven very successful for face verification and clustering tasks. Assuming that face and voices from the same identities share some latent properties (like age, gender, ethnicity), we propose three transfer learning approaches to leverage the knowledge from the face domain (learned from thousands of images and identities) for tasks in 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":"1707.02749","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-07-10T08:51:53Z","cross_cats_sorted":[],"title_canon_sha256":"4627fc4d915fc926fda4eabafd1c36eb989ab33cd2eddc34daeafec37b3c4b43","abstract_canon_sha256":"b99fcb0ec33a4bd6a3903d46964f52a30ebaceb81958700801feea949007dba1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:35.901001Z","signature_b64":"AwHX5p1VVBGtPGCzSd22TVeuaBqgEj47QOwH+7QQiXwJHYthH4uVbVKnb3hKTqGOS+AK5N5BRA5Yj1oByFMtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6579158424a8f1e637627f49d0efd21cbcf6721150b379594bce335db6908ead","last_reissued_at":"2026-05-18T00:40:35.900230Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:35.900230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving speaker turn embedding by crossmodal transfer learning from face embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jean-Marc Odobez, Nam Le","submitted_at":"2017-07-10T08:51:53Z","abstract_excerpt":"Learning speaker turn embeddings has shown considerable improvement in situations where conventional speaker modeling approaches fail. However, this improvement is relatively limited when compared to the gain observed in face embedding learning, which has been proven very successful for face verification and clustering tasks. Assuming that face and voices from the same identities share some latent properties (like age, gender, ethnicity), we propose three transfer learning approaches to leverage the knowledge from the face domain (learned from thousands of images and identities) for tasks in t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.02749","kind":"arxiv","version":1},"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":"1707.02749","created_at":"2026-05-18T00:40:35.900360+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.02749v1","created_at":"2026-05-18T00:40:35.900360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.02749","created_at":"2026-05-18T00:40:35.900360+00:00"},{"alias_kind":"pith_short_12","alias_value":"MV4RLBBEVDY6","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"MV4RLBBEVDY6MN3C","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"MV4RLBBE","created_at":"2026-05-18T12:31:31.346846+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/MV4RLBBEVDY6MN3CP5E5B36SDS","json":"https://pith.science/pith/MV4RLBBEVDY6MN3CP5E5B36SDS.json","graph_json":"https://pith.science/api/pith-number/MV4RLBBEVDY6MN3CP5E5B36SDS/graph.json","events_json":"https://pith.science/api/pith-number/MV4RLBBEVDY6MN3CP5E5B36SDS/events.json","paper":"https://pith.science/paper/MV4RLBBE"},"agent_actions":{"view_html":"https://pith.science/pith/MV4RLBBEVDY6MN3CP5E5B36SDS","download_json":"https://pith.science/pith/MV4RLBBEVDY6MN3CP5E5B36SDS.json","view_paper":"https://pith.science/paper/MV4RLBBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.02749&json=true","fetch_graph":"https://pith.science/api/pith-number/MV4RLBBEVDY6MN3CP5E5B36SDS/graph.json","fetch_events":"https://pith.science/api/pith-number/MV4RLBBEVDY6MN3CP5E5B36SDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MV4RLBBEVDY6MN3CP5E5B36SDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MV4RLBBEVDY6MN3CP5E5B36SDS/action/storage_attestation","attest_author":"https://pith.science/pith/MV4RLBBEVDY6MN3CP5E5B36SDS/action/author_attestation","sign_citation":"https://pith.science/pith/MV4RLBBEVDY6MN3CP5E5B36SDS/action/citation_signature","submit_replication":"https://pith.science/pith/MV4RLBBEVDY6MN3CP5E5B36SDS/action/replication_record"}},"created_at":"2026-05-18T00:40:35.900360+00:00","updated_at":"2026-05-18T00:40:35.900360+00:00"}