{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XB5CPIL6DGS3IFXKGHCEDSQKH3","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":"5d77c363866a7cbe2cc9eaa86a489be720dc16b3814f674f5c245bc420a83221","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-08T16:12:38Z","title_canon_sha256":"ad16db0ff7be682472b66614e3297b71390e3562ca40fd6562ea7475c40eaea1"},"schema_version":"1.0","source":{"id":"2211.04346","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.04346","created_at":"2026-07-05T05:14:28Z"},{"alias_kind":"arxiv_version","alias_value":"2211.04346v1","created_at":"2026-07-05T05:14:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.04346","created_at":"2026-07-05T05:14:28Z"},{"alias_kind":"pith_short_12","alias_value":"XB5CPIL6DGS3","created_at":"2026-07-05T05:14:28Z"},{"alias_kind":"pith_short_16","alias_value":"XB5CPIL6DGS3IFXK","created_at":"2026-07-05T05:14:28Z"},{"alias_kind":"pith_short_8","alias_value":"XB5CPIL6","created_at":"2026-07-05T05:14:28Z"}],"graph_snapshots":[{"event_id":"sha256:0dcdef7dd1a57791d5854325a651e6ca27d40a58244591e2ba859869483e1147","target":"graph","created_at":"2026-07-05T05:14:28Z","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/2211.04346/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalised speech enhancement (PSE), which extracts only the speech of a target user and removes everything else from a recorded audio clip, can potentially improve users' experiences of audio AI modules deployed in the wild. To support a large variety of downstream audio tasks, such as real-time ASR and audio-call enhancement, a PSE solution should operate in a streaming mode, i.e., input audio cleaning should happen in real-time with a small latency and real-time factor. Personalisation is typically achieved by extracting a target speaker's voice profile from an enrolment audio, in the for","authors_text":"Alberto Gil C. P. Ramos, Malcolm Chadwick, Shucong Zhang, Sourav Bhattacharya","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-08T16:12:38Z","title":"Cross-Attention is all you need: Real-Time Streaming Transformers for Personalised Speech Enhancement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.04346","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:def74598dae13e7d0e5ffb4181abc2cf3ed3fe43252c508cfbb40dcc61c80443","target":"record","created_at":"2026-07-05T05:14:28Z","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":"5d77c363866a7cbe2cc9eaa86a489be720dc16b3814f674f5c245bc420a83221","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2022-11-08T16:12:38Z","title_canon_sha256":"ad16db0ff7be682472b66614e3297b71390e3562ca40fd6562ea7475c40eaea1"},"schema_version":"1.0","source":{"id":"2211.04346","kind":"arxiv","version":1}},"canonical_sha256":"b87a27a17e19a5b416ea31c441ca0a3eede6c458a42b1c0760f2fc9bd203d966","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b87a27a17e19a5b416ea31c441ca0a3eede6c458a42b1c0760f2fc9bd203d966","first_computed_at":"2026-07-05T05:14:28.756078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:14:28.756078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M/IDs02uR4mDup0ovTorDV1t094qqq66VTir0gbPOOWGvFp3SAJ2ycl9DbiYdZAwH+JDu9s8jquxkwlS422iCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:14:28.756541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.04346","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:def74598dae13e7d0e5ffb4181abc2cf3ed3fe43252c508cfbb40dcc61c80443","sha256:0dcdef7dd1a57791d5854325a651e6ca27d40a58244591e2ba859869483e1147"],"state_sha256":"cdc34420cd75e5af333eeabbd3ededd7099058284b2831342343f5f9af1d959c"}