{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XPXSLPWYIBLBG7WZMGDBXHPQCQ","short_pith_number":"pith:XPXSLPWY","schema_version":"1.0","canonical_sha256":"bbef25bed84056137ed961861b9df01434e4148cb2df806377b0c8da2529916d","source":{"kind":"arxiv","id":"2211.05564","version":1},"attestation_state":"computed","paper":{"title":"Self-supervised learning with bi-label masked speech prediction for streaming multi-talker speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Peidong Wang, Takuya Yoshioka, Xiaofei Wang, Yiming Wang, Zhuo Chen, Zili Huang","submitted_at":"2022-11-10T13:36:27Z","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"},"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":"2211.05564","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-10T13:36:27Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"74ceb2e67db6ea0d2a180889d87c0de3c1c7a527f4b6c2c125597ce471f5f5f4","abstract_canon_sha256":"91a4d2baec298c246b7c549aad5099c1e6733f543bbddb4b12e5c24549e0b29e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:05.857473Z","signature_b64":"P0rIrpG5wfx7m/ykOWiFQMdTpafWxWSIlPJYn4bETqyypjxODX2toyrqjzh7MZcPe2ueLVTjvGVFUPD/xJvlCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbef25bed84056137ed961861b9df01434e4148cb2df806377b0c8da2529916d","last_reissued_at":"2026-07-05T05:15:05.857102Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:05.857102Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-supervised learning with bi-label masked speech prediction for streaming multi-talker speech recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Jian Wu, Jinyu Li, Naoyuki Kanda, Peidong Wang, Takuya Yoshioka, Xiaofei Wang, Yiming Wang, Zhuo Chen, Zili Huang","submitted_at":"2022-11-10T13:36:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05564","kind":"arxiv","version":1},"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/2211.05564/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":"2211.05564","created_at":"2026-07-05T05:15:05.857156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.05564v1","created_at":"2026-07-05T05:15:05.857156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05564","created_at":"2026-07-05T05:15:05.857156+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPXSLPWYIBLB","created_at":"2026-07-05T05:15:05.857156+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPXSLPWYIBLBG7WZ","created_at":"2026-07-05T05:15:05.857156+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPXSLPWY","created_at":"2026-07-05T05:15:05.857156+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/XPXSLPWYIBLBG7WZMGDBXHPQCQ","json":"https://pith.science/pith/XPXSLPWYIBLBG7WZMGDBXHPQCQ.json","graph_json":"https://pith.science/api/pith-number/XPXSLPWYIBLBG7WZMGDBXHPQCQ/graph.json","events_json":"https://pith.science/api/pith-number/XPXSLPWYIBLBG7WZMGDBXHPQCQ/events.json","paper":"https://pith.science/paper/XPXSLPWY"},"agent_actions":{"view_html":"https://pith.science/pith/XPXSLPWYIBLBG7WZMGDBXHPQCQ","download_json":"https://pith.science/pith/XPXSLPWYIBLBG7WZMGDBXHPQCQ.json","view_paper":"https://pith.science/paper/XPXSLPWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.05564&json=true","fetch_graph":"https://pith.science/api/pith-number/XPXSLPWYIBLBG7WZMGDBXHPQCQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XPXSLPWYIBLBG7WZMGDBXHPQCQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPXSLPWYIBLBG7WZMGDBXHPQCQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPXSLPWYIBLBG7WZMGDBXHPQCQ/action/storage_attestation","attest_author":"https://pith.science/pith/XPXSLPWYIBLBG7WZMGDBXHPQCQ/action/author_attestation","sign_citation":"https://pith.science/pith/XPXSLPWYIBLBG7WZMGDBXHPQCQ/action/citation_signature","submit_replication":"https://pith.science/pith/XPXSLPWYIBLBG7WZMGDBXHPQCQ/action/replication_record"}},"created_at":"2026-07-05T05:15:05.857156+00:00","updated_at":"2026-07-05T05:15:05.857156+00:00"}