{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ENEDPZORTUHQ54LBA73VVOJKZS","short_pith_number":"pith:ENEDPZOR","schema_version":"1.0","canonical_sha256":"234837e5d19d0f0ef16107f75ab92acc84bd4e6af52d9b1982f96fe5aa792991","source":{"kind":"arxiv","id":"2012.01551","version":1},"attestation_state":"computed","paper":{"title":"Joint gender and age estimation based on speech signals using x-vectors and transfer learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Damian Kwasny, Daria Hemmerling","submitted_at":"2020-12-02T21:46:01Z","abstract_excerpt":"In this paper we extend the x-vector framework for the task of speaker's age estimation and gender classification. In particular, we replace the baseline multilayer-TDNN architecture with QuartzNet, a convolutional architecture that has gained success in the field of speech recognition. We further propose a two-staged transfer learning scheme, utilizing large scale speech datasets: VoxCeleb and Common Voice, and usage of multitask learning to allow for joint age estimation and gender classification with a single system. We train and evaluate the performance on the TIMIT dataset. The proposed 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":"2012.01551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-12-02T21:46:01Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"6457af0864ebc1998366b682eb8197410ef84186d3414ce87775d79ad48dc8a2","abstract_canon_sha256":"3ff2769b5e4528612c85e6bc533b7e3998ec4805a8510c158e992d20cbeaa354"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:56:47.519071Z","signature_b64":"dQ6lNoOzG5J9Aj2nikwKp0/lgmevuP97JKzcFftiOnv0o7xtEaf4pd7NXJ+fBcYkP/ax0yxQ9iOpdAX2olviBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"234837e5d19d0f0ef16107f75ab92acc84bd4e6af52d9b1982f96fe5aa792991","last_reissued_at":"2026-07-05T01:56:47.518732Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:56:47.518732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Joint gender and age estimation based on speech signals using x-vectors and transfer learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Damian Kwasny, Daria Hemmerling","submitted_at":"2020-12-02T21:46:01Z","abstract_excerpt":"In this paper we extend the x-vector framework for the task of speaker's age estimation and gender classification. In particular, we replace the baseline multilayer-TDNN architecture with QuartzNet, a convolutional architecture that has gained success in the field of speech recognition. We further propose a two-staged transfer learning scheme, utilizing large scale speech datasets: VoxCeleb and Common Voice, and usage of multitask learning to allow for joint age estimation and gender classification with a single system. We train and evaluate the performance on the TIMIT dataset. The proposed t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.01551","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.01551/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":"2012.01551","created_at":"2026-07-05T01:56:47.518784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.01551v1","created_at":"2026-07-05T01:56:47.518784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.01551","created_at":"2026-07-05T01:56:47.518784+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENEDPZORTUHQ","created_at":"2026-07-05T01:56:47.518784+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENEDPZORTUHQ54LB","created_at":"2026-07-05T01:56:47.518784+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENEDPZOR","created_at":"2026-07-05T01:56:47.518784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09229","citing_title":"Tessellated Linear Model for Age Prediction from Voice","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENEDPZORTUHQ54LBA73VVOJKZS","json":"https://pith.science/pith/ENEDPZORTUHQ54LBA73VVOJKZS.json","graph_json":"https://pith.science/api/pith-number/ENEDPZORTUHQ54LBA73VVOJKZS/graph.json","events_json":"https://pith.science/api/pith-number/ENEDPZORTUHQ54LBA73VVOJKZS/events.json","paper":"https://pith.science/paper/ENEDPZOR"},"agent_actions":{"view_html":"https://pith.science/pith/ENEDPZORTUHQ54LBA73VVOJKZS","download_json":"https://pith.science/pith/ENEDPZORTUHQ54LBA73VVOJKZS.json","view_paper":"https://pith.science/paper/ENEDPZOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.01551&json=true","fetch_graph":"https://pith.science/api/pith-number/ENEDPZORTUHQ54LBA73VVOJKZS/graph.json","fetch_events":"https://pith.science/api/pith-number/ENEDPZORTUHQ54LBA73VVOJKZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENEDPZORTUHQ54LBA73VVOJKZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENEDPZORTUHQ54LBA73VVOJKZS/action/storage_attestation","attest_author":"https://pith.science/pith/ENEDPZORTUHQ54LBA73VVOJKZS/action/author_attestation","sign_citation":"https://pith.science/pith/ENEDPZORTUHQ54LBA73VVOJKZS/action/citation_signature","submit_replication":"https://pith.science/pith/ENEDPZORTUHQ54LBA73VVOJKZS/action/replication_record"}},"created_at":"2026-07-05T01:56:47.518784+00:00","updated_at":"2026-07-05T01:56:47.518784+00:00"}