{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SQ6Z4QJVNFW2GP4JIOU5MPGNJC","short_pith_number":"pith:SQ6Z4QJV","schema_version":"1.0","canonical_sha256":"943d9e4135696da33f8943a9d63ccd4895c38297d1372d1bfb9e1f79fc1b7586","source":{"kind":"arxiv","id":"2206.06680","version":2},"attestation_state":"computed","paper":{"title":"Exploring speaker enrolment for few-shot personalisation in emotional vocalisation prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Meishu Song, Xin Jing, Zijiang Yang","submitted_at":"2022-06-14T08:15:16Z","abstract_excerpt":"In this work, we explore a novel few-shot personalisation architecture for emotional vocalisation prediction. The core contribution is an `enrolment' encoder which utilises two unlabelled samples of the target speaker to adjust the output of the emotion encoder; the adjustment is based on dot-product attention, thus effectively functioning as a form of `soft' feature selection. The emotion and enrolment encoders are based on two standard audio architectures: CNN14 and CNN10. The two encoders are further guided to forget or learn auxiliary emotion and/or speaker information. Our best approach 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":"2206.06680","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2022-06-14T08:15:16Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"d3007b797c0193e82bdd779de5f794d09392d6e4987e9903f64a3301b716351a","abstract_canon_sha256":"ccbd8acd7b1c28cf7c22aeec8c13c08e84d265dac51882f37ed0afb02f288989"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:01.318675Z","signature_b64":"6LB9Oz23HC/oZnD0FwcdEhglk0nNI82b8TygRxEUA3oJyNlPzNxcU1M6fz+Pz9FB6FpYyvGOk5rLZbJhRGejCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"943d9e4135696da33f8943a9d63ccd4895c38297d1372d1bfb9e1f79fc1b7586","last_reissued_at":"2026-07-05T04:33:01.318114Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:01.318114Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring speaker enrolment for few-shot personalisation in emotional vocalisation prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Andreas Triantafyllopoulos, Bj\\\"orn W. Schuller, Meishu Song, Xin Jing, Zijiang Yang","submitted_at":"2022-06-14T08:15:16Z","abstract_excerpt":"In this work, we explore a novel few-shot personalisation architecture for emotional vocalisation prediction. The core contribution is an `enrolment' encoder which utilises two unlabelled samples of the target speaker to adjust the output of the emotion encoder; the adjustment is based on dot-product attention, thus effectively functioning as a form of `soft' feature selection. The emotion and enrolment encoders are based on two standard audio architectures: CNN14 and CNN10. The two encoders are further guided to forget or learn auxiliary emotion and/or speaker information. Our best approach a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06680","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/2206.06680/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":"2206.06680","created_at":"2026-07-05T04:33:01.318200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.06680v2","created_at":"2026-07-05T04:33:01.318200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06680","created_at":"2026-07-05T04:33:01.318200+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQ6Z4QJVNFW2","created_at":"2026-07-05T04:33:01.318200+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQ6Z4QJVNFW2GP4J","created_at":"2026-07-05T04:33:01.318200+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQ6Z4QJV","created_at":"2026-07-05T04:33:01.318200+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/SQ6Z4QJVNFW2GP4JIOU5MPGNJC","json":"https://pith.science/pith/SQ6Z4QJVNFW2GP4JIOU5MPGNJC.json","graph_json":"https://pith.science/api/pith-number/SQ6Z4QJVNFW2GP4JIOU5MPGNJC/graph.json","events_json":"https://pith.science/api/pith-number/SQ6Z4QJVNFW2GP4JIOU5MPGNJC/events.json","paper":"https://pith.science/paper/SQ6Z4QJV"},"agent_actions":{"view_html":"https://pith.science/pith/SQ6Z4QJVNFW2GP4JIOU5MPGNJC","download_json":"https://pith.science/pith/SQ6Z4QJVNFW2GP4JIOU5MPGNJC.json","view_paper":"https://pith.science/paper/SQ6Z4QJV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.06680&json=true","fetch_graph":"https://pith.science/api/pith-number/SQ6Z4QJVNFW2GP4JIOU5MPGNJC/graph.json","fetch_events":"https://pith.science/api/pith-number/SQ6Z4QJVNFW2GP4JIOU5MPGNJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQ6Z4QJVNFW2GP4JIOU5MPGNJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQ6Z4QJVNFW2GP4JIOU5MPGNJC/action/storage_attestation","attest_author":"https://pith.science/pith/SQ6Z4QJVNFW2GP4JIOU5MPGNJC/action/author_attestation","sign_citation":"https://pith.science/pith/SQ6Z4QJVNFW2GP4JIOU5MPGNJC/action/citation_signature","submit_replication":"https://pith.science/pith/SQ6Z4QJVNFW2GP4JIOU5MPGNJC/action/replication_record"}},"created_at":"2026-07-05T04:33:01.318200+00:00","updated_at":"2026-07-05T04:33:01.318200+00:00"}