{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YSQJRUBSFUGIADRQ326XE4HGD4","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":"dd89e3b42f2d76f7bd8dc897cedcb77bf7cde6d2bbfb9c72127a9b6a5fc66f7f","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-18T23:16:23Z","title_canon_sha256":"e9428e74fe8896949dc29c7da6483ca39104284ef1e0fee8865b2784526200b0"},"schema_version":"1.0","source":{"id":"2409.12352","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12352","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12352v1","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12352","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"pith_short_12","alias_value":"YSQJRUBSFUGI","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"pith_short_16","alias_value":"YSQJRUBSFUGIADRQ","created_at":"2026-07-05T09:08:52Z"},{"alias_kind":"pith_short_8","alias_value":"YSQJRUBS","created_at":"2026-07-05T09:08:52Z"}],"graph_snapshots":[{"event_id":"sha256:dddb1c51f0c49ed3ff51f2795f1e08bdeaa6115d47e18a38dc42b3ac6be5fd43","target":"graph","created_at":"2026-07-05T09:08:52Z","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/2409.12352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel end-to-end multi-talker automatic speech recognition (ASR) framework that enables both multi-speaker (MS) ASR and target-speaker (TS) ASR. Our proposed model is trained in a fully end-to-end manner, incorporating speaker supervision from a pre-trained speaker diarization module. We introduce an intuitive yet effective method for masking ASR encoder activations using output from the speaker supervision module, a technique we term Meta-Cat (meta-information concatenation), that can be applied to both MS-ASR and TS-ASR. Our results demonstrate that the proposed architecture ach","authors_text":"Boris Ginsburg, He Huang, Ivan Medennikov, Jagadeesh Balam, Jinhan Wang, Kunal Dhawan, Myungjong Kim, Nithin Koluguri, Taejin Park, Weiqing Wang","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-18T23:16:23Z","title":"META-CAT: Speaker-Informed Speech Embeddings via Meta Information Concatenation for Multi-talker ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12352","kind":"arxiv","version":1},"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":"sha256:2d5ddf67515d12c9d4abae881d293f5e4a97a70eb7394589def5a47b7d862013","target":"record","created_at":"2026-07-05T09:08:52Z","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":"dd89e3b42f2d76f7bd8dc897cedcb77bf7cde6d2bbfb9c72127a9b6a5fc66f7f","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-09-18T23:16:23Z","title_canon_sha256":"e9428e74fe8896949dc29c7da6483ca39104284ef1e0fee8865b2784526200b0"},"schema_version":"1.0","source":{"id":"2409.12352","kind":"arxiv","version":1}},"canonical_sha256":"c4a098d0322d0c800e30debd7270e61f0d4bf067edf3d9e82bca68659ca8b464","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c4a098d0322d0c800e30debd7270e61f0d4bf067edf3d9e82bca68659ca8b464","first_computed_at":"2026-07-05T09:08:52.571543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:08:52.571543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rpb1JWvO8nzUvKPMjzUMlx3sKNn5e4IqVHEZoVitYesTOjQevoDCUmQaFNGSDenlZ2YZRoB2cBtQgmvOrdCCCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:08:52.572050Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12352","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d5ddf67515d12c9d4abae881d293f5e4a97a70eb7394589def5a47b7d862013","sha256:dddb1c51f0c49ed3ff51f2795f1e08bdeaa6115d47e18a38dc42b3ac6be5fd43"],"state_sha256":"5d3e1eeab2dfb1080c55b02292dd535bb976f40662d6174b6685cfb58a28b817"}