{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LD74FP66RQSAL6L3DRMSHKGRHU","short_pith_number":"pith:LD74FP66","schema_version":"1.0","canonical_sha256":"58ffc2bfde8c2405f97b1c5923a8d13d10964fc2d896a412058e6d6de8515968","source":{"kind":"arxiv","id":"2209.04974","version":2},"attestation_state":"computed","paper":{"title":"VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Zhuo Chen","submitted_at":"2022-09-12T01:22:04Z","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"},"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":"2209.04974","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-09-12T01:22:04Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"315c1dccc304a12df2f29b58b8f0ac996efcecaaeeca8f5c9a27fc7fbb0479ff","abstract_canon_sha256":"5acb24c2f9e249d9b6f539b9f697a9504d1e8fdfbbee5b0ec2e2621a002e1c27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:05.858683Z","signature_b64":"n+ePN26fDx9hdXDy4GpA9WAsTAlUaHy+bei4qb/da8M847pt6F7qKgQzetx2Nft/6b3hiyufr/vN7dcSMTeXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58ffc2bfde8c2405f97b1c5923a8d13d10964fc2d896a412058e6d6de8515968","last_reissued_at":"2026-07-05T05:03:05.858287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:05.858287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Takuya Yoshioka, Xiaofei Wang, Zhuo Chen","submitted_at":"2022-09-12T01:22:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04974","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/2209.04974/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":"2209.04974","created_at":"2026-07-05T05:03:05.858355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.04974v2","created_at":"2026-07-05T05:03:05.858355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04974","created_at":"2026-07-05T05:03:05.858355+00:00"},{"alias_kind":"pith_short_12","alias_value":"LD74FP66RQSA","created_at":"2026-07-05T05:03:05.858355+00:00"},{"alias_kind":"pith_short_16","alias_value":"LD74FP66RQSAL6L3","created_at":"2026-07-05T05:03:05.858355+00:00"},{"alias_kind":"pith_short_8","alias_value":"LD74FP66","created_at":"2026-07-05T05:03:05.858355+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/LD74FP66RQSAL6L3DRMSHKGRHU","json":"https://pith.science/pith/LD74FP66RQSAL6L3DRMSHKGRHU.json","graph_json":"https://pith.science/api/pith-number/LD74FP66RQSAL6L3DRMSHKGRHU/graph.json","events_json":"https://pith.science/api/pith-number/LD74FP66RQSAL6L3DRMSHKGRHU/events.json","paper":"https://pith.science/paper/LD74FP66"},"agent_actions":{"view_html":"https://pith.science/pith/LD74FP66RQSAL6L3DRMSHKGRHU","download_json":"https://pith.science/pith/LD74FP66RQSAL6L3DRMSHKGRHU.json","view_paper":"https://pith.science/paper/LD74FP66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.04974&json=true","fetch_graph":"https://pith.science/api/pith-number/LD74FP66RQSAL6L3DRMSHKGRHU/graph.json","fetch_events":"https://pith.science/api/pith-number/LD74FP66RQSAL6L3DRMSHKGRHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LD74FP66RQSAL6L3DRMSHKGRHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LD74FP66RQSAL6L3DRMSHKGRHU/action/storage_attestation","attest_author":"https://pith.science/pith/LD74FP66RQSAL6L3DRMSHKGRHU/action/author_attestation","sign_citation":"https://pith.science/pith/LD74FP66RQSAL6L3DRMSHKGRHU/action/citation_signature","submit_replication":"https://pith.science/pith/LD74FP66RQSAL6L3DRMSHKGRHU/action/replication_record"}},"created_at":"2026-07-05T05:03:05.858355+00:00","updated_at":"2026-07-05T05:03:05.858355+00:00"}