{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NDNN74MA5LKQ3Z5AY6EEC24AVC","short_pith_number":"pith:NDNN74MA","schema_version":"1.0","canonical_sha256":"68dadff180ead50de7a0c788416b80a89e70fe8f40a99915468c9a33c0017faa","source":{"kind":"arxiv","id":"1810.12620","version":1},"attestation_state":"computed","paper":{"title":"Towards End-to-end Automatic Code-Switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Chien-Sheng Wu, Genta Indra Winata, Pascale Fung","submitted_at":"2018-10-30T10:11:35Z","abstract_excerpt":"Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as \"one\" in English and \"w\\`an\" in Chinese. We propose a CTC-based end-to-end automatic speech recognition model for intra-sentential English-Mandarin code-switching. The model is trained by joint training on monolingual datasets, and fine-tuning with the mixed-language corpus. During the decoding process, we apply a beam search and combine CTC predictions and language model score. The proposed method is effective in leveraging monoli"},"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":"1810.12620","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T10:11:35Z","cross_cats_sorted":[],"title_canon_sha256":"d77dd16ee1d7beba33a2adc11fc4084a29974c72f37baddf83731509c4a27310","abstract_canon_sha256":"da1fdbb681dc5178d62a150f0d042845d928ebfe060f726490ad471eaeb839a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:56.507258Z","signature_b64":"VveXHM55mlNBmN96fJDLznTivLZjWiRpCJh4g1EDTMLnkS6b4knzmh1FLokMXc4OuFIySo4TqIBXEcS+IcQRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68dadff180ead50de7a0c788416b80a89e70fe8f40a99915468c9a33c0017faa","last_reissued_at":"2026-05-18T00:01:56.506783Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:56.506783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards End-to-end Automatic Code-Switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Chien-Sheng Wu, Genta Indra Winata, Pascale Fung","submitted_at":"2018-10-30T10:11:35Z","abstract_excerpt":"Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as \"one\" in English and \"w\\`an\" in Chinese. We propose a CTC-based end-to-end automatic speech recognition model for intra-sentential English-Mandarin code-switching. The model is trained by joint training on monolingual datasets, and fine-tuning with the mixed-language corpus. During the decoding process, we apply a beam search and combine CTC predictions and language model score. The proposed method is effective in leveraging monoli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12620","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":""},"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":"1810.12620","created_at":"2026-05-18T00:01:56.506851+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12620v1","created_at":"2026-05-18T00:01:56.506851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12620","created_at":"2026-05-18T00:01:56.506851+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDNN74MA5LKQ","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDNN74MA5LKQ3Z5A","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDNN74MA","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09426","citing_title":"End-to-End ASR for Code-switched Hindi-English Speech","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NDNN74MA5LKQ3Z5AY6EEC24AVC","json":"https://pith.science/pith/NDNN74MA5LKQ3Z5AY6EEC24AVC.json","graph_json":"https://pith.science/api/pith-number/NDNN74MA5LKQ3Z5AY6EEC24AVC/graph.json","events_json":"https://pith.science/api/pith-number/NDNN74MA5LKQ3Z5AY6EEC24AVC/events.json","paper":"https://pith.science/paper/NDNN74MA"},"agent_actions":{"view_html":"https://pith.science/pith/NDNN74MA5LKQ3Z5AY6EEC24AVC","download_json":"https://pith.science/pith/NDNN74MA5LKQ3Z5AY6EEC24AVC.json","view_paper":"https://pith.science/paper/NDNN74MA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12620&json=true","fetch_graph":"https://pith.science/api/pith-number/NDNN74MA5LKQ3Z5AY6EEC24AVC/graph.json","fetch_events":"https://pith.science/api/pith-number/NDNN74MA5LKQ3Z5AY6EEC24AVC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDNN74MA5LKQ3Z5AY6EEC24AVC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDNN74MA5LKQ3Z5AY6EEC24AVC/action/storage_attestation","attest_author":"https://pith.science/pith/NDNN74MA5LKQ3Z5AY6EEC24AVC/action/author_attestation","sign_citation":"https://pith.science/pith/NDNN74MA5LKQ3Z5AY6EEC24AVC/action/citation_signature","submit_replication":"https://pith.science/pith/NDNN74MA5LKQ3Z5AY6EEC24AVC/action/replication_record"}},"created_at":"2026-05-18T00:01:56.506851+00:00","updated_at":"2026-05-18T00:01:56.506851+00:00"}