{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:J2H55MPMBAOHW6IXMNKAX4M23Q","short_pith_number":"pith:J2H55MPM","schema_version":"1.0","canonical_sha256":"4e8fdeb1ec081c7b791763540bf19adc175b6ca4ef29d106b936250859fe4c97","source":{"kind":"arxiv","id":"2302.12773","version":2},"attestation_state":"computed","paper":{"title":"Towards multi-task learning of speech and speaker recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"David A. van Leeuwen, Nik Vaessen","submitted_at":"2023-02-24T17:42:25Z","abstract_excerpt":"We study multi-task learning for two orthogonal speech technology tasks: speech and speaker recognition. We use wav2vec2 as a base architecture with two task-specific output heads. We experiment with different architectural decisions to mix speaker and speech information in the output sequence as well as different optimization strategies. Our multi-task learning networks can produce a shared speaker and speech embedding, which on first glance achieve a performance comparable to separate single-task models. However, we show that the multi-task networks have strongly degraded performance on out-"},"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":"2302.12773","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-02-24T17:42:25Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3cf698c93670e8cddf6297f82dc726bd33628768b923454a66ab43eea2db0068","abstract_canon_sha256":"019d1a46c1fbd8bcf7fe5f10ae51481f7be86efe03512db46abcc4c88664491a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:08.768650Z","signature_b64":"cmzOBveauzvKK5Zw3HHtT0Cm/WKVagTYV0/efDesPxY7nqKzLF9Xc0otWKW83GBFBCKb2fTDl29SQt4qsUj3Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e8fdeb1ec081c7b791763540bf19adc175b6ca4ef29d106b936250859fe4c97","last_reissued_at":"2026-07-05T06:14:08.768231Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:08.768231Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards multi-task learning of speech and speaker recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"David A. van Leeuwen, Nik Vaessen","submitted_at":"2023-02-24T17:42:25Z","abstract_excerpt":"We study multi-task learning for two orthogonal speech technology tasks: speech and speaker recognition. We use wav2vec2 as a base architecture with two task-specific output heads. We experiment with different architectural decisions to mix speaker and speech information in the output sequence as well as different optimization strategies. Our multi-task learning networks can produce a shared speaker and speech embedding, which on first glance achieve a performance comparable to separate single-task models. However, we show that the multi-task networks have strongly degraded performance on out-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.12773","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/2302.12773/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":"2302.12773","created_at":"2026-07-05T06:14:08.768287+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.12773v2","created_at":"2026-07-05T06:14:08.768287+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.12773","created_at":"2026-07-05T06:14:08.768287+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2H55MPMBAOH","created_at":"2026-07-05T06:14:08.768287+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2H55MPMBAOHW6IX","created_at":"2026-07-05T06:14:08.768287+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2H55MPM","created_at":"2026-07-05T06:14:08.768287+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/J2H55MPMBAOHW6IXMNKAX4M23Q","json":"https://pith.science/pith/J2H55MPMBAOHW6IXMNKAX4M23Q.json","graph_json":"https://pith.science/api/pith-number/J2H55MPMBAOHW6IXMNKAX4M23Q/graph.json","events_json":"https://pith.science/api/pith-number/J2H55MPMBAOHW6IXMNKAX4M23Q/events.json","paper":"https://pith.science/paper/J2H55MPM"},"agent_actions":{"view_html":"https://pith.science/pith/J2H55MPMBAOHW6IXMNKAX4M23Q","download_json":"https://pith.science/pith/J2H55MPMBAOHW6IXMNKAX4M23Q.json","view_paper":"https://pith.science/paper/J2H55MPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.12773&json=true","fetch_graph":"https://pith.science/api/pith-number/J2H55MPMBAOHW6IXMNKAX4M23Q/graph.json","fetch_events":"https://pith.science/api/pith-number/J2H55MPMBAOHW6IXMNKAX4M23Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2H55MPMBAOHW6IXMNKAX4M23Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2H55MPMBAOHW6IXMNKAX4M23Q/action/storage_attestation","attest_author":"https://pith.science/pith/J2H55MPMBAOHW6IXMNKAX4M23Q/action/author_attestation","sign_citation":"https://pith.science/pith/J2H55MPMBAOHW6IXMNKAX4M23Q/action/citation_signature","submit_replication":"https://pith.science/pith/J2H55MPMBAOHW6IXMNKAX4M23Q/action/replication_record"}},"created_at":"2026-07-05T06:14:08.768287+00:00","updated_at":"2026-07-05T06:14:08.768287+00:00"}