{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XPXSLPWYIBLBG7WZMGDBXHPQCQ","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":"91a4d2baec298c246b7c549aad5099c1e6733f543bbddb4b12e5c24549e0b29e","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-10T13:36:27Z","title_canon_sha256":"74ceb2e67db6ea0d2a180889d87c0de3c1c7a527f4b6c2c125597ce471f5f5f4"},"schema_version":"1.0","source":{"id":"2211.05564","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.05564","created_at":"2026-07-05T05:15:05Z"},{"alias_kind":"arxiv_version","alias_value":"2211.05564v1","created_at":"2026-07-05T05:15:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05564","created_at":"2026-07-05T05:15:05Z"},{"alias_kind":"pith_short_12","alias_value":"XPXSLPWYIBLB","created_at":"2026-07-05T05:15:05Z"},{"alias_kind":"pith_short_16","alias_value":"XPXSLPWYIBLBG7WZ","created_at":"2026-07-05T05:15:05Z"},{"alias_kind":"pith_short_8","alias_value":"XPXSLPWY","created_at":"2026-07-05T05:15:05Z"}],"graph_snapshots":[{"event_id":"sha256:a0e50b724f52ca90e48b7496ffd7d47c6c1f105ddd17cd7eee30554823625bbb","target":"graph","created_at":"2026-07-05T05:15:05Z","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/2211.05564/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervised learning (SSL), which utilizes the input data itself for representation learning, has achieved state-of-the-art results for various downstream speech tasks. However, most of the previous studies focused on offline single-talker applications, with limited investigations in multi-talker cases, especially for streaming scenarios. In this paper, we investigate SSL for streaming multi-talker speech recognition, which generates transcriptions of overlapping speakers in a streaming fashion. We first observe that conventional SSL techniques do not work well on this task due to the poor","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Peidong Wang, Takuya Yoshioka, Xiaofei Wang, Yiming Wang, Zhuo Chen, Zili Huang","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-10T13:36:27Z","title":"Self-supervised learning with bi-label masked speech prediction for streaming multi-talker speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05564","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":"sha256:96486d9596d894bcdf5077f5d2a8af667c1646d680330bb405838d2f72fd323f","target":"record","created_at":"2026-07-05T05:15:05Z","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":"91a4d2baec298c246b7c549aad5099c1e6733f543bbddb4b12e5c24549e0b29e","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-10T13:36:27Z","title_canon_sha256":"74ceb2e67db6ea0d2a180889d87c0de3c1c7a527f4b6c2c125597ce471f5f5f4"},"schema_version":"1.0","source":{"id":"2211.05564","kind":"arxiv","version":1}},"canonical_sha256":"bbef25bed84056137ed961861b9df01434e4148cb2df806377b0c8da2529916d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbef25bed84056137ed961861b9df01434e4148cb2df806377b0c8da2529916d","first_computed_at":"2026-07-05T05:15:05.857102Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:05.857102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P0rIrpG5wfx7m/ykOWiFQMdTpafWxWSIlPJYn4bETqyypjxODX2toyrqjzh7MZcPe2ueLVTjvGVFUPD/xJvlCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:05.857473Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.05564","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96486d9596d894bcdf5077f5d2a8af667c1646d680330bb405838d2f72fd323f","sha256:a0e50b724f52ca90e48b7496ffd7d47c6c1f105ddd17cd7eee30554823625bbb"],"state_sha256":"53c7508f1d2e0e49f267b0b51fa2bd9d16c8b8c097a616b7297c51058eefe917"}