{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CKO3XXT4ZR5LY23MSRW7SOSAQ6","short_pith_number":"pith:CKO3XXT4","canonical_record":{"source":{"id":"2407.09817","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-13T09:28:24Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"66fb6917464ef60838bdc42309dced77a6b87ef7b4a2b4bedc86c2f03ffa7158","abstract_canon_sha256":"f642eb86110ad14cd4646f3c914ad15ac8f8941540856b0f9d6d59de642fe00f"},"schema_version":"1.0"},"canonical_sha256":"129dbbde7ccc7abc6b6c946df93a40879e9222e36bbf416282de8025a22f7fe4","source":{"kind":"arxiv","id":"2407.09817","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09817","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09817v2","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09817","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"CKO3XXT4ZR5L","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"CKO3XXT4ZR5LY23M","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"CKO3XXT4","created_at":"2026-07-05T08:58:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CKO3XXT4ZR5LY23MSRW7SOSAQ6","target":"record","payload":{"canonical_record":{"source":{"id":"2407.09817","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-13T09:28:24Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"66fb6917464ef60838bdc42309dced77a6b87ef7b4a2b4bedc86c2f03ffa7158","abstract_canon_sha256":"f642eb86110ad14cd4646f3c914ad15ac8f8941540856b0f9d6d59de642fe00f"},"schema_version":"1.0"},"canonical_sha256":"129dbbde7ccc7abc6b6c946df93a40879e9222e36bbf416282de8025a22f7fe4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:45.521618Z","signature_b64":"uqAsy09meXvXgl+H1Pj2A2FzRPDgrw0XaOUOSo5fMooB4dx5LvlRoyP5KLDePlZ99H9K4FMdH7fTwxV1T+/VDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"129dbbde7ccc7abc6b6c946df93a40879e9222e36bbf416282de8025a22f7fe4","last_reissued_at":"2026-07-05T08:58:45.521106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:45.521106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.09817","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mwboalqfYoWyKdKGP1ZagcTbu10+IXGglgLbxM1/ntTYIdsvcVY7aqXcjsOR3BypdjLYZsYob8h8a5r++uYpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:09:54.645582Z"},"content_sha256":"0c7dbac1413757063decde32be1c537728be0234c3c8ce3ea2bd0bc67e9f9ae1","schema_version":"1.0","event_id":"sha256:0c7dbac1413757063decde32be1c537728be0234c3c8ce3ea2bd0bc67e9f9ae1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CKO3XXT4ZR5LY23MSRW7SOSAQ6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Helen Meng, Jiawen Kang, Lingwei Meng, Xixin Wu, Xunying Liu, Yuejiao Wang, Zengrui Jin","submitted_at":"2024-07-13T09:28:24Z","abstract_excerpt":"Multi-talker speech recognition and target-talker speech recognition, both involve transcription in multi-talker contexts, remain significant challenges. However, existing methods rarely attempt to simultaneously address both tasks. In this study, we propose a pioneering approach to empower Whisper, which is a speech foundation model, to tackle joint multi-talker and target-talker speech recognition tasks. Specifically, (i) we freeze Whisper and plug a Sidecar separator into its encoder to separate mixed embedding for multiple talkers; (ii) a Target Talker Identifier is introduced to identify "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09817","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/2407.09817/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:58:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ExjsnfpbVnf5xc47dgNu2wSVCHeSyy3fLpyXBFjFO6WSg8V7BMKvRii0rrTgzDVm/F6ZSR4BadayqPqsv/4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:09:54.646091Z"},"content_sha256":"04863c9545ae7378ee5cfb1bc1df54c695471b3487a49e4a83bfe814d75a8e57","schema_version":"1.0","event_id":"sha256:04863c9545ae7378ee5cfb1bc1df54c695471b3487a49e4a83bfe814d75a8e57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKO3XXT4ZR5LY23MSRW7SOSAQ6/bundle.json","state_url":"https://pith.science/pith/CKO3XXT4ZR5LY23MSRW7SOSAQ6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKO3XXT4ZR5LY23MSRW7SOSAQ6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-10T09:09:54Z","links":{"resolver":"https://pith.science/pith/CKO3XXT4ZR5LY23MSRW7SOSAQ6","bundle":"https://pith.science/pith/CKO3XXT4ZR5LY23MSRW7SOSAQ6/bundle.json","state":"https://pith.science/pith/CKO3XXT4ZR5LY23MSRW7SOSAQ6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKO3XXT4ZR5LY23MSRW7SOSAQ6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CKO3XXT4ZR5LY23MSRW7SOSAQ6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f642eb86110ad14cd4646f3c914ad15ac8f8941540856b0f9d6d59de642fe00f","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-13T09:28:24Z","title_canon_sha256":"66fb6917464ef60838bdc42309dced77a6b87ef7b4a2b4bedc86c2f03ffa7158"},"schema_version":"1.0","source":{"id":"2407.09817","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.09817","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"arxiv_version","alias_value":"2407.09817v2","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09817","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"pith_short_12","alias_value":"CKO3XXT4ZR5L","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"pith_short_16","alias_value":"CKO3XXT4ZR5LY23M","created_at":"2026-07-05T08:58:45Z"},{"alias_kind":"pith_short_8","alias_value":"CKO3XXT4","created_at":"2026-07-05T08:58:45Z"}],"graph_snapshots":[{"event_id":"sha256:04863c9545ae7378ee5cfb1bc1df54c695471b3487a49e4a83bfe814d75a8e57","target":"graph","created_at":"2026-07-05T08:58:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2407.09817/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-talker speech recognition and target-talker speech recognition, both involve transcription in multi-talker contexts, remain significant challenges. However, existing methods rarely attempt to simultaneously address both tasks. In this study, we propose a pioneering approach to empower Whisper, which is a speech foundation model, to tackle joint multi-talker and target-talker speech recognition tasks. Specifically, (i) we freeze Whisper and plug a Sidecar separator into its encoder to separate mixed embedding for multiple talkers; (ii) a Target Talker Identifier is introduced to identify ","authors_text":"Helen Meng, Jiawen Kang, Lingwei Meng, Xixin Wu, Xunying Liu, Yuejiao Wang, Zengrui Jin","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-13T09:28:24Z","title":"Empowering Whisper as a Joint Multi-Talker and Target-Talker Speech Recognition System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09817","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0c7dbac1413757063decde32be1c537728be0234c3c8ce3ea2bd0bc67e9f9ae1","target":"record","created_at":"2026-07-05T08:58:45Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f642eb86110ad14cd4646f3c914ad15ac8f8941540856b0f9d6d59de642fe00f","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-07-13T09:28:24Z","title_canon_sha256":"66fb6917464ef60838bdc42309dced77a6b87ef7b4a2b4bedc86c2f03ffa7158"},"schema_version":"1.0","source":{"id":"2407.09817","kind":"arxiv","version":2}},"canonical_sha256":"129dbbde7ccc7abc6b6c946df93a40879e9222e36bbf416282de8025a22f7fe4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"129dbbde7ccc7abc6b6c946df93a40879e9222e36bbf416282de8025a22f7fe4","first_computed_at":"2026-07-05T08:58:45.521106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:58:45.521106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uqAsy09meXvXgl+H1Pj2A2FzRPDgrw0XaOUOSo5fMooB4dx5LvlRoyP5KLDePlZ99H9K4FMdH7fTwxV1T+/VDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:58:45.521618Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.09817","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c7dbac1413757063decde32be1c537728be0234c3c8ce3ea2bd0bc67e9f9ae1","sha256:04863c9545ae7378ee5cfb1bc1df54c695471b3487a49e4a83bfe814d75a8e57"],"state_sha256":"eb771ea35c587366c04a403a49d9a023fd4531fa494671c3c08ac549bd9e4440"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yNykZEOvJ+eSyPQazy4PLofx4cQ7NlFYdZ2YkwIZ7g+T8iMU/c9EVfEhFx6/AlUkVeVwoTTQXmD7gsQiOcuiBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:09:54.651061Z","bundle_sha256":"78de98daf6fc5d4255289c29f709824537b0285b124b8d89354527c793df9cba"}}