{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:25NEMHA5OO5SRJ2TZRDFDIJ4FJ","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":"28020f21e8deefb5a3d08dba5a8dced31437d46955df0930a47c5da13c933df6","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-09T20:51:54Z","title_canon_sha256":"1408d07f6b170c8a8c02c288abdec68f38022cbae75453feac76f8e16615378c"},"schema_version":"1.0","source":{"id":"2308.05218","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.05218","created_at":"2026-07-05T06:39:57Z"},{"alias_kind":"arxiv_version","alias_value":"2308.05218v1","created_at":"2026-07-05T06:39:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05218","created_at":"2026-07-05T06:39:57Z"},{"alias_kind":"pith_short_12","alias_value":"25NEMHA5OO5S","created_at":"2026-07-05T06:39:57Z"},{"alias_kind":"pith_short_16","alias_value":"25NEMHA5OO5SRJ2T","created_at":"2026-07-05T06:39:57Z"},{"alias_kind":"pith_short_8","alias_value":"25NEMHA5","created_at":"2026-07-05T06:39:57Z"}],"graph_snapshots":[{"event_id":"sha256:1cefb51de118fbea35d87c5311a3d79c6f6cb1d304cdcc630022b6db9c55b31e","target":"graph","created_at":"2026-07-05T06:39:57Z","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/2308.05218/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose CONF-TSASR, a non-autoregressive end-to-end time-frequency domain architecture for single-channel target-speaker automatic speech recognition (TS-ASR). The model consists of a TitaNet based speaker embedding module, a Conformer based masking as well as ASR modules. These modules are jointly optimized to transcribe a target-speaker, while ignoring speech from other speakers. For training we use Connectionist Temporal Classification (CTC) loss and introduce a scale-invariant spectrogram reconstruction loss to encourage the model better separate the target-speaker's spectrogram from mi","authors_text":"Boris Ginsburg, Krishna C. Puvvada, Vitaly Lavrukhin, Yang Zhang","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-09T20:51:54Z","title":"Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05218","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":"sha256:243aa234844027b0f7a426e0fb2894a4dcc49ac10b7477cf92379a1718753eb5","target":"record","created_at":"2026-07-05T06:39:57Z","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":"28020f21e8deefb5a3d08dba5a8dced31437d46955df0930a47c5da13c933df6","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-09T20:51:54Z","title_canon_sha256":"1408d07f6b170c8a8c02c288abdec68f38022cbae75453feac76f8e16615378c"},"schema_version":"1.0","source":{"id":"2308.05218","kind":"arxiv","version":1}},"canonical_sha256":"d75a461c1d73bb28a753cc4651a13c2a684287a8142de7437d8b5fa68a4f841a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d75a461c1d73bb28a753cc4651a13c2a684287a8142de7437d8b5fa68a4f841a","first_computed_at":"2026-07-05T06:39:57.237701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:39:57.237701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MJo0den1+wfzspdPXlGXasttQrlyTyOD14fymB1h1040hwMSbJL9OaM55k2MBZ+SEdOMT8dhttwcW3r0TOCMCA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:39:57.238134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.05218","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:243aa234844027b0f7a426e0fb2894a4dcc49ac10b7477cf92379a1718753eb5","sha256:1cefb51de118fbea35d87c5311a3d79c6f6cb1d304cdcc630022b6db9c55b31e"],"state_sha256":"61aaaa5f4b2c758cc02cc1233ae2b7552e37aef123a8dbcf65043c1bcde80362"}