{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VO2Z3BTCKNJUURRZN2C2YDAWQU","short_pith_number":"pith:VO2Z3BTC","schema_version":"1.0","canonical_sha256":"abb59d866253534a46396e85ac0c16851007dc09aee4d4f87205aeab1364256c","source":{"kind":"arxiv","id":"2411.17846","version":1},"attestation_state":"computed","paper":{"title":"Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Pu Wang","submitted_at":"2024-11-26T19:57:40Z","abstract_excerpt":"End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the explainable Disentangled-Transformer, which disentangles the internal representations into sub-embeddings with explicit content and speaker traits based on varying temporal resolutions. Experimental results show that the proposed Disentangled-Transformer produces a clear speaker identity, separated from the speech content, for speaker diarization while improvi"},"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":"2411.17846","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-11-26T19:57:40Z","cross_cats_sorted":[],"title_canon_sha256":"506f7c9d65e677c0c5640bb21a64e89a11e2bcdcc8dcee169759ba8605d47881","abstract_canon_sha256":"66a0b9ccf412f0098239517f5ad95bb22ac2580b60956fb9fd3d4ec39fc408f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:07.801508Z","signature_b64":"25bU2OZcWqoCsBNyu5Zwwctr2Qg581f7gWan7m9QBXR8Qq6IMANEePmfg835B2vG/05jJUrLqiJylDhDh972Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abb59d866253534a46396e85ac0c16851007dc09aee4d4f87205aeab1364256c","last_reissued_at":"2026-07-05T09:41:07.801065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:07.801065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangled-Transformer: An Explainable End-to-End Automatic Speech Recognition Model with Speech Content-Context Separation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hugo Van hamme, Pu Wang","submitted_at":"2024-11-26T19:57:40Z","abstract_excerpt":"End-to-end transformer-based automatic speech recognition (ASR) systems often capture multiple speech traits in their learned representations that are highly entangled, leading to a lack of interpretability. In this study, we propose the explainable Disentangled-Transformer, which disentangles the internal representations into sub-embeddings with explicit content and speaker traits based on varying temporal resolutions. Experimental results show that the proposed Disentangled-Transformer produces a clear speaker identity, separated from the speech content, for speaker diarization while improvi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.17846","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/2411.17846/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":"2411.17846","created_at":"2026-07-05T09:41:07.801119+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.17846v1","created_at":"2026-07-05T09:41:07.801119+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.17846","created_at":"2026-07-05T09:41:07.801119+00:00"},{"alias_kind":"pith_short_12","alias_value":"VO2Z3BTCKNJU","created_at":"2026-07-05T09:41:07.801119+00:00"},{"alias_kind":"pith_short_16","alias_value":"VO2Z3BTCKNJUURRZ","created_at":"2026-07-05T09:41:07.801119+00:00"},{"alias_kind":"pith_short_8","alias_value":"VO2Z3BTC","created_at":"2026-07-05T09:41:07.801119+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/VO2Z3BTCKNJUURRZN2C2YDAWQU","json":"https://pith.science/pith/VO2Z3BTCKNJUURRZN2C2YDAWQU.json","graph_json":"https://pith.science/api/pith-number/VO2Z3BTCKNJUURRZN2C2YDAWQU/graph.json","events_json":"https://pith.science/api/pith-number/VO2Z3BTCKNJUURRZN2C2YDAWQU/events.json","paper":"https://pith.science/paper/VO2Z3BTC"},"agent_actions":{"view_html":"https://pith.science/pith/VO2Z3BTCKNJUURRZN2C2YDAWQU","download_json":"https://pith.science/pith/VO2Z3BTCKNJUURRZN2C2YDAWQU.json","view_paper":"https://pith.science/paper/VO2Z3BTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.17846&json=true","fetch_graph":"https://pith.science/api/pith-number/VO2Z3BTCKNJUURRZN2C2YDAWQU/graph.json","fetch_events":"https://pith.science/api/pith-number/VO2Z3BTCKNJUURRZN2C2YDAWQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VO2Z3BTCKNJUURRZN2C2YDAWQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VO2Z3BTCKNJUURRZN2C2YDAWQU/action/storage_attestation","attest_author":"https://pith.science/pith/VO2Z3BTCKNJUURRZN2C2YDAWQU/action/author_attestation","sign_citation":"https://pith.science/pith/VO2Z3BTCKNJUURRZN2C2YDAWQU/action/citation_signature","submit_replication":"https://pith.science/pith/VO2Z3BTCKNJUURRZN2C2YDAWQU/action/replication_record"}},"created_at":"2026-07-05T09:41:07.801119+00:00","updated_at":"2026-07-05T09:41:07.801119+00:00"}