{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CYQXGDSSAHMEACYY763ODS4KJC","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":"bbccca61f0d3aa617837891ab381b94fbabcaf684173c1c149cbcb2b0df08ef7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-09T08:21:41Z","title_canon_sha256":"f52b188644ba2ff78d4fcbdcf87f0bea8dcf6d75a371f669b86dff237948caec"},"schema_version":"1.0","source":{"id":"2209.04175","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.04175","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"arxiv_version","alias_value":"2209.04175v2","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04175","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"pith_short_12","alias_value":"CYQXGDSSAHME","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"pith_short_16","alias_value":"CYQXGDSSAHMEACYY","created_at":"2026-07-05T04:58:39Z"},{"alias_kind":"pith_short_8","alias_value":"CYQXGDSS","created_at":"2026-07-05T04:58:39Z"}],"graph_snapshots":[{"event_id":"sha256:51ff6bcf8dcf5635398dd73c2ff808eb94d0ee0a57125edc3f1a63a0143b09ad","target":"graph","created_at":"2026-07-05T04:58:39Z","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/2209.04175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although recent advances in deep learning technology have boosted automatic speech recognition (ASR) performance in the single-talker case, it remains difficult to recognize multi-talker speech in which many voices overlap. One conventional approach to tackle this problem is to use a cascade of a speech separation or target speech extraction front-end with an ASR back-end. However, the extra computation costs of the front-end module are a critical barrier to quick response, especially for streaming ASR. In this paper, we propose a target-speaker ASR (TS-ASR) system that implicitly integrates t","authors_text":"Hiroshi Sato, Marc Delcroix, Takafumi Moriya, Takahiro Shinozaki, Tsubasa Ochiai","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-09T08:21:41Z","title":"Streaming Target-Speaker ASR with Neural Transducer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04175","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:c5aa8f71ae893d3d9f25dc8a63f8a70951cf42b9624d53b2b259919c074eac64","target":"record","created_at":"2026-07-05T04:58:39Z","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":"bbccca61f0d3aa617837891ab381b94fbabcaf684173c1c149cbcb2b0df08ef7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2022-09-09T08:21:41Z","title_canon_sha256":"f52b188644ba2ff78d4fcbdcf87f0bea8dcf6d75a371f669b86dff237948caec"},"schema_version":"1.0","source":{"id":"2209.04175","kind":"arxiv","version":2}},"canonical_sha256":"1621730e5201d8400b18ffb6e1cb8a48a74c142ecad2a7df82574197680263b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1621730e5201d8400b18ffb6e1cb8a48a74c142ecad2a7df82574197680263b8","first_computed_at":"2026-07-05T04:58:39.322806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:58:39.322806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CDyBPZbcZT/N12hydq3EifuSYQpNY44RZMMkqIQNTQf/L7x9YEgr5klwF1UsF7HGL5WaDo5/KMTGy0ok79kcBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:58:39.323221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.04175","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5aa8f71ae893d3d9f25dc8a63f8a70951cf42b9624d53b2b259919c074eac64","sha256:51ff6bcf8dcf5635398dd73c2ff808eb94d0ee0a57125edc3f1a63a0143b09ad"],"state_sha256":"738a1d349e2c32a64d52371b65955362cba32816228bebc1692aad244bcce6f0"}