{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5LTJS3A634KFUYNB24ATAD2ON6","short_pith_number":"pith:5LTJS3A6","schema_version":"1.0","canonical_sha256":"eae6996c1edf145a61a1d701300f4e6f8529cef485e82e2b1a7fa673a3afd4b5","source":{"kind":"arxiv","id":"2211.01046","version":1},"attestation_state":"computed","paper":{"title":"Monolingual Recognizers Fusion for Code-switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hao Shi, Haoyu Lu, Jianwu Dang, Longbiao Wang, Qiang Xu, Tongtong Song, Yanbing Yang, Yuqin Lin","submitted_at":"2022-11-02T11:24:26Z","abstract_excerpt":"The bi-encoder structure has been intensively investigated in code-switching (CS) automatic speech recognition (ASR). However, most existing methods require the structures of two monolingual ASR models (MAMs) should be the same and only use the encoder of MAMs. This leads to the problem that pre-trained MAMs cannot be timely and fully used for CS ASR. In this paper, we propose a monolingual recognizers fusion method for CS ASR. It has two stages: the speech awareness (SA) stage and the language fusion (LF) stage. In the SA stage, acoustic features are mapped to two language-specific prediction"},"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":"2211.01046","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-11-02T11:24:26Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"377abd9bbe6b843e7a85957da972efada3dd73442c2df8a0378eb8d9949e0b2d","abstract_canon_sha256":"126c0a7b1bb13f5688ab864a4b18bcc104b70cdc5b01bb023c47e6a3b802c49c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:12:37.646422Z","signature_b64":"JBV0V85WOZtLuLmNNKRJPbcfqCAee3A68Q/gc84yv7/22NDv+1rzlrmVGxXXIxsLlEpHeGFAVpTffi8um9QMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eae6996c1edf145a61a1d701300f4e6f8529cef485e82e2b1a7fa673a3afd4b5","last_reissued_at":"2026-07-05T05:12:37.646010Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:12:37.646010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Monolingual Recognizers Fusion for Code-switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Hao Shi, Haoyu Lu, Jianwu Dang, Longbiao Wang, Qiang Xu, Tongtong Song, Yanbing Yang, Yuqin Lin","submitted_at":"2022-11-02T11:24:26Z","abstract_excerpt":"The bi-encoder structure has been intensively investigated in code-switching (CS) automatic speech recognition (ASR). However, most existing methods require the structures of two monolingual ASR models (MAMs) should be the same and only use the encoder of MAMs. This leads to the problem that pre-trained MAMs cannot be timely and fully used for CS ASR. In this paper, we propose a monolingual recognizers fusion method for CS ASR. It has two stages: the speech awareness (SA) stage and the language fusion (LF) stage. In the SA stage, acoustic features are mapped to two language-specific prediction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01046","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/2211.01046/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":"2211.01046","created_at":"2026-07-05T05:12:37.646075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.01046v1","created_at":"2026-07-05T05:12:37.646075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01046","created_at":"2026-07-05T05:12:37.646075+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LTJS3A634KF","created_at":"2026-07-05T05:12:37.646075+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LTJS3A634KFUYNB","created_at":"2026-07-05T05:12:37.646075+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LTJS3A6","created_at":"2026-07-05T05:12:37.646075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.16507","citing_title":"Adapting Whisper for Code-Switching through Encoding Refining and Language-Aware Decoding","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5LTJS3A634KFUYNB24ATAD2ON6","json":"https://pith.science/pith/5LTJS3A634KFUYNB24ATAD2ON6.json","graph_json":"https://pith.science/api/pith-number/5LTJS3A634KFUYNB24ATAD2ON6/graph.json","events_json":"https://pith.science/api/pith-number/5LTJS3A634KFUYNB24ATAD2ON6/events.json","paper":"https://pith.science/paper/5LTJS3A6"},"agent_actions":{"view_html":"https://pith.science/pith/5LTJS3A634KFUYNB24ATAD2ON6","download_json":"https://pith.science/pith/5LTJS3A634KFUYNB24ATAD2ON6.json","view_paper":"https://pith.science/paper/5LTJS3A6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.01046&json=true","fetch_graph":"https://pith.science/api/pith-number/5LTJS3A634KFUYNB24ATAD2ON6/graph.json","fetch_events":"https://pith.science/api/pith-number/5LTJS3A634KFUYNB24ATAD2ON6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LTJS3A634KFUYNB24ATAD2ON6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LTJS3A634KFUYNB24ATAD2ON6/action/storage_attestation","attest_author":"https://pith.science/pith/5LTJS3A634KFUYNB24ATAD2ON6/action/author_attestation","sign_citation":"https://pith.science/pith/5LTJS3A634KFUYNB24ATAD2ON6/action/citation_signature","submit_replication":"https://pith.science/pith/5LTJS3A634KFUYNB24ATAD2ON6/action/replication_record"}},"created_at":"2026-07-05T05:12:37.646075+00:00","updated_at":"2026-07-05T05:12:37.646075+00:00"}