{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T5DZGXUFHXCB3W5LSQZZECF6R2","short_pith_number":"pith:T5DZGXUF","schema_version":"1.0","canonical_sha256":"9f47935e853dc41ddbab94339208be8e876238705bca904c859b57d3b8750564","source":{"kind":"arxiv","id":"2501.05989","version":1},"attestation_state":"computed","paper":{"title":"Addressing speaker gender bias in large scale speech translation systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Harveen Chadha, Jinyu Li, Rupeshkumar Mehta, Shubham Bansal, Vikas Joshi","submitted_at":"2025-01-10T14:20:46Z","abstract_excerpt":"This study addresses the issue of speaker gender bias in Speech Translation (ST) systems, which can lead to offensive and inaccurate translations. The masculine bias often found in large-scale ST systems is typically perpetuated through training data derived from Machine Translation (MT) systems. Our approach involves two key steps. First, we employ Large Language Models (LLMs) to rectify translations based on the speaker's gender in a cost-effective manner. Second, we fine-tune the ST model with the corrected data, enabling the model to generate gender-specific translations directly from audi"},"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":"2501.05989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-10T14:20:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e85715396531503a3d93bd3b0acd56a058c31bba77506508bd07c3eadbdde57c","abstract_canon_sha256":"9367554d1d437c7b24abfc4aa149db023358a51df9aaa94fd11f52a5c68a1b42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:31.219601Z","signature_b64":"d6C9heARv2GIILHQ7BlAbeFH0CY95oiyclqEpegAqc8ZneyZBBLR+vgbdhfLEa4YfzupcEIigaq7N+11FrV3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f47935e853dc41ddbab94339208be8e876238705bca904c859b57d3b8750564","last_reissued_at":"2026-07-05T09:59:31.219135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:31.219135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Addressing speaker gender bias in large scale speech translation systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Harveen Chadha, Jinyu Li, Rupeshkumar Mehta, Shubham Bansal, Vikas Joshi","submitted_at":"2025-01-10T14:20:46Z","abstract_excerpt":"This study addresses the issue of speaker gender bias in Speech Translation (ST) systems, which can lead to offensive and inaccurate translations. The masculine bias often found in large-scale ST systems is typically perpetuated through training data derived from Machine Translation (MT) systems. Our approach involves two key steps. First, we employ Large Language Models (LLMs) to rectify translations based on the speaker's gender in a cost-effective manner. Second, we fine-tune the ST model with the corrected data, enabling the model to generate gender-specific translations directly from audi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05989","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/2501.05989/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":"2501.05989","created_at":"2026-07-05T09:59:31.219198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05989v1","created_at":"2026-07-05T09:59:31.219198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05989","created_at":"2026-07-05T09:59:31.219198+00:00"},{"alias_kind":"pith_short_12","alias_value":"T5DZGXUFHXCB","created_at":"2026-07-05T09:59:31.219198+00:00"},{"alias_kind":"pith_short_16","alias_value":"T5DZGXUFHXCB3W5L","created_at":"2026-07-05T09:59:31.219198+00:00"},{"alias_kind":"pith_short_8","alias_value":"T5DZGXUF","created_at":"2026-07-05T09:59:31.219198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.21517","citing_title":"Voice, Bias, and Coreference: An Interpretability Study of Gender in Speech Translation","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T5DZGXUFHXCB3W5LSQZZECF6R2","json":"https://pith.science/pith/T5DZGXUFHXCB3W5LSQZZECF6R2.json","graph_json":"https://pith.science/api/pith-number/T5DZGXUFHXCB3W5LSQZZECF6R2/graph.json","events_json":"https://pith.science/api/pith-number/T5DZGXUFHXCB3W5LSQZZECF6R2/events.json","paper":"https://pith.science/paper/T5DZGXUF"},"agent_actions":{"view_html":"https://pith.science/pith/T5DZGXUFHXCB3W5LSQZZECF6R2","download_json":"https://pith.science/pith/T5DZGXUFHXCB3W5LSQZZECF6R2.json","view_paper":"https://pith.science/paper/T5DZGXUF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05989&json=true","fetch_graph":"https://pith.science/api/pith-number/T5DZGXUFHXCB3W5LSQZZECF6R2/graph.json","fetch_events":"https://pith.science/api/pith-number/T5DZGXUFHXCB3W5LSQZZECF6R2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T5DZGXUFHXCB3W5LSQZZECF6R2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T5DZGXUFHXCB3W5LSQZZECF6R2/action/storage_attestation","attest_author":"https://pith.science/pith/T5DZGXUFHXCB3W5LSQZZECF6R2/action/author_attestation","sign_citation":"https://pith.science/pith/T5DZGXUFHXCB3W5LSQZZECF6R2/action/citation_signature","submit_replication":"https://pith.science/pith/T5DZGXUFHXCB3W5LSQZZECF6R2/action/replication_record"}},"created_at":"2026-07-05T09:59:31.219198+00:00","updated_at":"2026-07-05T09:59:31.219198+00:00"}