{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:LD74FP66RQSAL6L3DRMSHKGRHU","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":"5acb24c2f9e249d9b6f539b9f697a9504d1e8fdfbbee5b0ec2e2621a002e1c27","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-12T01:22:04Z","title_canon_sha256":"315c1dccc304a12df2f29b58b8f0ac996efcecaaeeca8f5c9a27fc7fbb0479ff"},"schema_version":"1.0","source":{"id":"2209.04974","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.04974","created_at":"2026-07-05T05:03:05Z"},{"alias_kind":"arxiv_version","alias_value":"2209.04974v2","created_at":"2026-07-05T05:03:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04974","created_at":"2026-07-05T05:03:05Z"},{"alias_kind":"pith_short_12","alias_value":"LD74FP66RQSA","created_at":"2026-07-05T05:03:05Z"},{"alias_kind":"pith_short_16","alias_value":"LD74FP66RQSAL6L3","created_at":"2026-07-05T05:03:05Z"},{"alias_kind":"pith_short_8","alias_value":"LD74FP66","created_at":"2026-07-05T05:03:05Z"}],"graph_snapshots":[{"event_id":"sha256:d9cc6a1b29d9c565d458f935c9fcc538350f15169d8975b8481b62ee3ab851ce","target":"graph","created_at":"2026-07-05T05:03:05Z","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/2209.04974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a novel streaming automatic speech recognition (ASR) framework for multi-talker overlapping speech captured by a distant microphone array with an arbitrary geometry. Our framework, named t-SOT-VA, capitalizes on independently developed two recent technologies; array-geometry-agnostic continuous speech separation, or VarArray, and streaming multi-talker ASR based on token-level serialized output training (t-SOT). To combine the best of both technologies, we newly design a t-SOT-based ASR model that generates a serialized multi-talker transcription based on two separated spee","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Zhuo Chen","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-12T01:22:04Z","title":"VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04974","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":"sha256:4d8a77585ebe86a88a062b0e6b8354a1bbd4e413d5bb6ea2a87b357da82f140f","target":"record","created_at":"2026-07-05T05:03:05Z","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":"5acb24c2f9e249d9b6f539b9f697a9504d1e8fdfbbee5b0ec2e2621a002e1c27","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-12T01:22:04Z","title_canon_sha256":"315c1dccc304a12df2f29b58b8f0ac996efcecaaeeca8f5c9a27fc7fbb0479ff"},"schema_version":"1.0","source":{"id":"2209.04974","kind":"arxiv","version":2}},"canonical_sha256":"58ffc2bfde8c2405f97b1c5923a8d13d10964fc2d896a412058e6d6de8515968","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58ffc2bfde8c2405f97b1c5923a8d13d10964fc2d896a412058e6d6de8515968","first_computed_at":"2026-07-05T05:03:05.858287Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:03:05.858287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n+ePN26fDx9hdXDy4GpA9WAsTAlUaHy+bei4qb/da8M847pt6F7qKgQzetx2Nft/6b3hiyufr/vN7dcSMTeXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:03:05.858683Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.04974","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d8a77585ebe86a88a062b0e6b8354a1bbd4e413d5bb6ea2a87b357da82f140f","sha256:d9cc6a1b29d9c565d458f935c9fcc538350f15169d8975b8481b62ee3ab851ce"],"state_sha256":"943bdc191733b5c363e4717013d4e92e405f41754ca7ce919fdead9b53868463"}