{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XC4VOBX2VSXTT2HDIX664IK2UA","short_pith_number":"pith:XC4VOBX2","schema_version":"1.0","canonical_sha256":"b8b95706faacaf39e8e345fdee215aa00b629ea0ec38943af8f899efa9ced068","source":{"kind":"arxiv","id":"2312.06055","version":1},"attestation_state":"computed","paper":{"title":"Speaker-Text Retrieval via Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Erica Cooper, Junichi Yamagishi, Xiaoxiao Miao, Xin Wang, Xuechen Liu","submitted_at":"2023-12-11T01:23:50Z","abstract_excerpt":"In this study, we introduce a novel cross-modal retrieval task involving speaker descriptions and their corresponding audio samples. Utilizing pre-trained speaker and text encoders, we present a simple learning framework based on contrastive learning. Additionally, we explore the impact of incorporating speaker labels into the training process. Our findings establish the effectiveness of linking speaker and text information for the task for both English and Japanese languages, across diverse data configurations. Additional visual analysis unveils potential nuanced associations between speaker "},"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":"2312.06055","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-12-11T01:23:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"182ed1a44936fb152dba4a29920fe201b3e8d45c044657ee4e8fb6398834052c","abstract_canon_sha256":"229683bdb6c1b3f25e6d0e85fe87f77cef1859c73f96c8654fbe42531b6a8f45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:37.617062Z","signature_b64":"C2M0+iJcuD45bwmQ9GEe5Km/vmykFjWAH/Nci9TrOpsekhgE64eIq84wtjorB+2j5bsNvD9MF7hpHL/lNhslBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8b95706faacaf39e8e345fdee215aa00b629ea0ec38943af8f899efa9ced068","last_reissued_at":"2026-07-05T07:22:37.616614Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:37.616614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speaker-Text Retrieval via Contrastive Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Erica Cooper, Junichi Yamagishi, Xiaoxiao Miao, Xin Wang, Xuechen Liu","submitted_at":"2023-12-11T01:23:50Z","abstract_excerpt":"In this study, we introduce a novel cross-modal retrieval task involving speaker descriptions and their corresponding audio samples. Utilizing pre-trained speaker and text encoders, we present a simple learning framework based on contrastive learning. Additionally, we explore the impact of incorporating speaker labels into the training process. Our findings establish the effectiveness of linking speaker and text information for the task for both English and Japanese languages, across diverse data configurations. Additional visual analysis unveils potential nuanced associations between speaker "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06055","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/2312.06055/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":"2312.06055","created_at":"2026-07-05T07:22:37.616688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06055v1","created_at":"2026-07-05T07:22:37.616688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06055","created_at":"2026-07-05T07:22:37.616688+00:00"},{"alias_kind":"pith_short_12","alias_value":"XC4VOBX2VSXT","created_at":"2026-07-05T07:22:37.616688+00:00"},{"alias_kind":"pith_short_16","alias_value":"XC4VOBX2VSXTT2HD","created_at":"2026-07-05T07:22:37.616688+00:00"},{"alias_kind":"pith_short_8","alias_value":"XC4VOBX2","created_at":"2026-07-05T07:22:37.616688+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03283","citing_title":"SpeakerCard-1M: An Evidence-Grounded Corpus for In-the-Wild Speaker Verification","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03283","citing_title":"SpeakerCard-1M: An Evidence-Grounded Corpus for In-the-Wild Speaker Verification","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XC4VOBX2VSXTT2HDIX664IK2UA","json":"https://pith.science/pith/XC4VOBX2VSXTT2HDIX664IK2UA.json","graph_json":"https://pith.science/api/pith-number/XC4VOBX2VSXTT2HDIX664IK2UA/graph.json","events_json":"https://pith.science/api/pith-number/XC4VOBX2VSXTT2HDIX664IK2UA/events.json","paper":"https://pith.science/paper/XC4VOBX2"},"agent_actions":{"view_html":"https://pith.science/pith/XC4VOBX2VSXTT2HDIX664IK2UA","download_json":"https://pith.science/pith/XC4VOBX2VSXTT2HDIX664IK2UA.json","view_paper":"https://pith.science/paper/XC4VOBX2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06055&json=true","fetch_graph":"https://pith.science/api/pith-number/XC4VOBX2VSXTT2HDIX664IK2UA/graph.json","fetch_events":"https://pith.science/api/pith-number/XC4VOBX2VSXTT2HDIX664IK2UA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XC4VOBX2VSXTT2HDIX664IK2UA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XC4VOBX2VSXTT2HDIX664IK2UA/action/storage_attestation","attest_author":"https://pith.science/pith/XC4VOBX2VSXTT2HDIX664IK2UA/action/author_attestation","sign_citation":"https://pith.science/pith/XC4VOBX2VSXTT2HDIX664IK2UA/action/citation_signature","submit_replication":"https://pith.science/pith/XC4VOBX2VSXTT2HDIX664IK2UA/action/replication_record"}},"created_at":"2026-07-05T07:22:37.616688+00:00","updated_at":"2026-07-05T07:22:37.616688+00:00"}