{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LB5MAGSS3TXEWJOYYELZ6W7X4Y","short_pith_number":"pith:LB5MAGSS","schema_version":"1.0","canonical_sha256":"587ac01a52dcee4b25d8c1179f5bf7e628f2c6252a9e05dce2589226ab55ee6f","source":{"kind":"arxiv","id":"1908.08717","version":1},"attestation_state":"computed","paper":{"title":"Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Laurent Besacier, Mahault Garnerin, Solange Rossato","submitted_at":"2019-08-23T08:51:19Z","abstract_excerpt":"This paper analyzes the gender representation in four major corpora of French broadcast. These corpora being widely used within the speech processing community, they are a primary material for training automatic speech recognition (ASR) systems. As gender bias has been highlighted in numerous natural language processing (NLP) applications, we study the impact of the gender imbalance in TV and radio broadcast on the performance of an ASR system. This analysis shows that women are under-represented in our data in terms of speakers and speech turns. We introduce the notion of speaker role to refi"},"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":"1908.08717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-23T08:51:19Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"57466cf6fc2c96342d081f41560f4441ef2030ee531c467ad7c21514227d3295","abstract_canon_sha256":"aea6955f98bfbe9c10330f3e4c2849368f35075bb4449f9527ad5fcae3d0f27f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:23.545562Z","signature_b64":"yymgBWlSWbRtfyWX5IqzuSBHeIja6Q5TSpZ+3h8x3i+2HECATTG0qS+mT2XYhWpPiQpQnRsDCAiV5jDMK05YCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"587ac01a52dcee4b25d8c1179f5bf7e628f2c6252a9e05dce2589226ab55ee6f","last_reissued_at":"2026-07-04T23:59:23.545156Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:23.545156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Laurent Besacier, Mahault Garnerin, Solange Rossato","submitted_at":"2019-08-23T08:51:19Z","abstract_excerpt":"This paper analyzes the gender representation in four major corpora of French broadcast. These corpora being widely used within the speech processing community, they are a primary material for training automatic speech recognition (ASR) systems. As gender bias has been highlighted in numerous natural language processing (NLP) applications, we study the impact of the gender imbalance in TV and radio broadcast on the performance of an ASR system. This analysis shows that women are under-represented in our data in terms of speakers and speech turns. We introduce the notion of speaker role to refi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08717","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/1908.08717/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":"1908.08717","created_at":"2026-07-04T23:59:23.545212+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.08717v1","created_at":"2026-07-04T23:59:23.545212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08717","created_at":"2026-07-04T23:59:23.545212+00:00"},{"alias_kind":"pith_short_12","alias_value":"LB5MAGSS3TXE","created_at":"2026-07-04T23:59:23.545212+00:00"},{"alias_kind":"pith_short_16","alias_value":"LB5MAGSS3TXEWJOY","created_at":"2026-07-04T23:59:23.545212+00:00"},{"alias_kind":"pith_short_8","alias_value":"LB5MAGSS","created_at":"2026-07-04T23:59:23.545212+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/LB5MAGSS3TXEWJOYYELZ6W7X4Y","json":"https://pith.science/pith/LB5MAGSS3TXEWJOYYELZ6W7X4Y.json","graph_json":"https://pith.science/api/pith-number/LB5MAGSS3TXEWJOYYELZ6W7X4Y/graph.json","events_json":"https://pith.science/api/pith-number/LB5MAGSS3TXEWJOYYELZ6W7X4Y/events.json","paper":"https://pith.science/paper/LB5MAGSS"},"agent_actions":{"view_html":"https://pith.science/pith/LB5MAGSS3TXEWJOYYELZ6W7X4Y","download_json":"https://pith.science/pith/LB5MAGSS3TXEWJOYYELZ6W7X4Y.json","view_paper":"https://pith.science/paper/LB5MAGSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.08717&json=true","fetch_graph":"https://pith.science/api/pith-number/LB5MAGSS3TXEWJOYYELZ6W7X4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/LB5MAGSS3TXEWJOYYELZ6W7X4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LB5MAGSS3TXEWJOYYELZ6W7X4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LB5MAGSS3TXEWJOYYELZ6W7X4Y/action/storage_attestation","attest_author":"https://pith.science/pith/LB5MAGSS3TXEWJOYYELZ6W7X4Y/action/author_attestation","sign_citation":"https://pith.science/pith/LB5MAGSS3TXEWJOYYELZ6W7X4Y/action/citation_signature","submit_replication":"https://pith.science/pith/LB5MAGSS3TXEWJOYYELZ6W7X4Y/action/replication_record"}},"created_at":"2026-07-04T23:59:23.545212+00:00","updated_at":"2026-07-04T23:59:23.545212+00:00"}