{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4766DFEO3EAOH6F67SV6EYBWTR","short_pith_number":"pith:4766DFEO","schema_version":"1.0","canonical_sha256":"e7fde1948ed900e3f8befcabe260369c6645e690a8d40a02a1809535fb49424c","source":{"kind":"arxiv","id":"2406.07012","version":2},"attestation_state":"computed","paper":{"title":"Bridging Language Gaps in Audio-Text Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Wang, Heinrich Dinkel, Jizhong Liu, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2024-06-11T07:12:12Z","abstract_excerpt":"Audio-text retrieval is a challenging task, requiring the search for an audio clip or a text caption within a database. The predominant focus of existing research on English descriptions poses a limitation on the applicability of such models, given the abundance of non-English content in real-world data. To address these linguistic disparities, we propose a language enhancement (LE), using a multilingual text encoder (SONAR) to encode the text data with language-specific information. Additionally, we optimize the audio encoder through the application of consistent ensemble distillation (CED), "},"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":"2406.07012","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-06-11T07:12:12Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"03408a39bcb8a0dba09a061dc41a314c06543635e1c1c96efd1691a3ecfeeafa","abstract_canon_sha256":"3a3b6230f5f60622118639c54023571685bb07b8f370f81833ea1e24d332a8ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:42.284816Z","signature_b64":"vKW4+NFOeNghH67TAOQ3yCgaJqjI/x0XPc6gFYHpmIPWIGwCqA/KeQAJWa/50O9ubk+k7z1e+rvpJ6GNY8xpAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7fde1948ed900e3f8befcabe260369c6645e690a8d40a02a1809535fb49424c","last_reissued_at":"2026-07-05T08:32:42.284339Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:42.284339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bridging Language Gaps in Audio-Text Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Wang, Heinrich Dinkel, Jizhong Liu, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2024-06-11T07:12:12Z","abstract_excerpt":"Audio-text retrieval is a challenging task, requiring the search for an audio clip or a text caption within a database. The predominant focus of existing research on English descriptions poses a limitation on the applicability of such models, given the abundance of non-English content in real-world data. To address these linguistic disparities, we propose a language enhancement (LE), using a multilingual text encoder (SONAR) to encode the text data with language-specific information. Additionally, we optimize the audio encoder through the application of consistent ensemble distillation (CED), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07012","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/2406.07012/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":"2406.07012","created_at":"2026-07-05T08:32:42.284392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07012v2","created_at":"2026-07-05T08:32:42.284392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07012","created_at":"2026-07-05T08:32:42.284392+00:00"},{"alias_kind":"pith_short_12","alias_value":"4766DFEO3EAO","created_at":"2026-07-05T08:32:42.284392+00:00"},{"alias_kind":"pith_short_16","alias_value":"4766DFEO3EAOH6F6","created_at":"2026-07-05T08:32:42.284392+00:00"},{"alias_kind":"pith_short_8","alias_value":"4766DFEO","created_at":"2026-07-05T08:32:42.284392+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/4766DFEO3EAOH6F67SV6EYBWTR","json":"https://pith.science/pith/4766DFEO3EAOH6F67SV6EYBWTR.json","graph_json":"https://pith.science/api/pith-number/4766DFEO3EAOH6F67SV6EYBWTR/graph.json","events_json":"https://pith.science/api/pith-number/4766DFEO3EAOH6F67SV6EYBWTR/events.json","paper":"https://pith.science/paper/4766DFEO"},"agent_actions":{"view_html":"https://pith.science/pith/4766DFEO3EAOH6F67SV6EYBWTR","download_json":"https://pith.science/pith/4766DFEO3EAOH6F67SV6EYBWTR.json","view_paper":"https://pith.science/paper/4766DFEO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07012&json=true","fetch_graph":"https://pith.science/api/pith-number/4766DFEO3EAOH6F67SV6EYBWTR/graph.json","fetch_events":"https://pith.science/api/pith-number/4766DFEO3EAOH6F67SV6EYBWTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4766DFEO3EAOH6F67SV6EYBWTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4766DFEO3EAOH6F67SV6EYBWTR/action/storage_attestation","attest_author":"https://pith.science/pith/4766DFEO3EAOH6F67SV6EYBWTR/action/author_attestation","sign_citation":"https://pith.science/pith/4766DFEO3EAOH6F67SV6EYBWTR/action/citation_signature","submit_replication":"https://pith.science/pith/4766DFEO3EAOH6F67SV6EYBWTR/action/replication_record"}},"created_at":"2026-07-05T08:32:42.284392+00:00","updated_at":"2026-07-05T08:32:42.284392+00:00"}