{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UGFC7N5GTDIFQVP76QWP67UFJF","short_pith_number":"pith:UGFC7N5G","schema_version":"1.0","canonical_sha256":"a18a2fb7a698d05855fff42cff7e85497fc42dde1093b147e7a652376eb34c71","source":{"kind":"arxiv","id":"2306.05279","version":1},"attestation_state":"computed","paper":{"title":"Language-specific Acoustic Boundary Learning for Mandarin-English Code-switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Chen Shen, Jun Zhang, Linhao Dong, Lu Lu, Zejun Ma, Zhenlin Liang, Zhiyun Fan","submitted_at":"2023-06-08T15:27:40Z","abstract_excerpt":"Code-switching speech recognition (CSSR) transcribes speech that switches between multiple languages or dialects within a single sentence. The main challenge in this task is that different languages often have similar pronunciations, making it difficult for models to distinguish between them. In this paper, we propose a method for solving the CSSR task from the perspective of language-specific acoustic boundary learning. We introduce language-specific weight estimators (LSWE) to model acoustic boundary learning in different languages separately. Additionally, a non-autoregressive (NAR) decoder"},"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":"2306.05279","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-08T15:27:40Z","cross_cats_sorted":[],"title_canon_sha256":"abdedb8ec48a7d2f18e734d3ba7d878dab8c6702fbfc246d98a3798a6df1cc38","abstract_canon_sha256":"be30b12e70c515aacfb4dd4deb42928a4f2d7cda3dd28eb30425a5f70290b8b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:18:54.817626Z","signature_b64":"NSNb6NfEVVPXfahH+Dtu1E4g24asEJZzYxgvEDwGidfWiUdYexgw0NSEfZ/rapIEwop1i6avIXPJtsZopDJ4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a18a2fb7a698d05855fff42cff7e85497fc42dde1093b147e7a652376eb34c71","last_reissued_at":"2026-07-05T06:18:54.817098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:18:54.817098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language-specific Acoustic Boundary Learning for Mandarin-English Code-switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Chen Shen, Jun Zhang, Linhao Dong, Lu Lu, Zejun Ma, Zhenlin Liang, Zhiyun Fan","submitted_at":"2023-06-08T15:27:40Z","abstract_excerpt":"Code-switching speech recognition (CSSR) transcribes speech that switches between multiple languages or dialects within a single sentence. The main challenge in this task is that different languages often have similar pronunciations, making it difficult for models to distinguish between them. In this paper, we propose a method for solving the CSSR task from the perspective of language-specific acoustic boundary learning. We introduce language-specific weight estimators (LSWE) to model acoustic boundary learning in different languages separately. Additionally, a non-autoregressive (NAR) decoder"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.05279","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/2306.05279/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":"2306.05279","created_at":"2026-07-05T06:18:54.817170+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05279v1","created_at":"2026-07-05T06:18:54.817170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05279","created_at":"2026-07-05T06:18:54.817170+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGFC7N5GTDIF","created_at":"2026-07-05T06:18:54.817170+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGFC7N5GTDIFQVP7","created_at":"2026-07-05T06:18:54.817170+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGFC7N5G","created_at":"2026-07-05T06:18:54.817170+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":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGFC7N5GTDIFQVP76QWP67UFJF","json":"https://pith.science/pith/UGFC7N5GTDIFQVP76QWP67UFJF.json","graph_json":"https://pith.science/api/pith-number/UGFC7N5GTDIFQVP76QWP67UFJF/graph.json","events_json":"https://pith.science/api/pith-number/UGFC7N5GTDIFQVP76QWP67UFJF/events.json","paper":"https://pith.science/paper/UGFC7N5G"},"agent_actions":{"view_html":"https://pith.science/pith/UGFC7N5GTDIFQVP76QWP67UFJF","download_json":"https://pith.science/pith/UGFC7N5GTDIFQVP76QWP67UFJF.json","view_paper":"https://pith.science/paper/UGFC7N5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05279&json=true","fetch_graph":"https://pith.science/api/pith-number/UGFC7N5GTDIFQVP76QWP67UFJF/graph.json","fetch_events":"https://pith.science/api/pith-number/UGFC7N5GTDIFQVP76QWP67UFJF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGFC7N5GTDIFQVP76QWP67UFJF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGFC7N5GTDIFQVP76QWP67UFJF/action/storage_attestation","attest_author":"https://pith.science/pith/UGFC7N5GTDIFQVP76QWP67UFJF/action/author_attestation","sign_citation":"https://pith.science/pith/UGFC7N5GTDIFQVP76QWP67UFJF/action/citation_signature","submit_replication":"https://pith.science/pith/UGFC7N5GTDIFQVP76QWP67UFJF/action/replication_record"}},"created_at":"2026-07-05T06:18:54.817170+00:00","updated_at":"2026-07-05T06:18:54.817170+00:00"}