{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CKG74OUNUFYBD5U636PUNKI23D","short_pith_number":"pith:CKG74OUN","canonical_record":{"source":{"id":"1806.06200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-16T07:18:22Z","cross_cats_sorted":[],"title_canon_sha256":"48db0a722473fd7a7c1d81b7b6403a9c3ffec7a3a4adad673fc46b83b63fc780","abstract_canon_sha256":"c267cd9a48012fcb16b93402a0d784306f519f2ade4b2de87a49ce0d629c8827"},"schema_version":"1.0"},"canonical_sha256":"128dfe3a8da17011f69edf9f46a91ad8d6a9fdeec816eab3de6a6c8fc1cbfcb0","source":{"kind":"arxiv","id":"1806.06200","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06200","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06200v1","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06200","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"CKG74OUNUFYB","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CKG74OUNUFYBD5U6","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CKG74OUN","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CKG74OUNUFYBD5U636PUNKI23D","target":"record","payload":{"canonical_record":{"source":{"id":"1806.06200","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-16T07:18:22Z","cross_cats_sorted":[],"title_canon_sha256":"48db0a722473fd7a7c1d81b7b6403a9c3ffec7a3a4adad673fc46b83b63fc780","abstract_canon_sha256":"c267cd9a48012fcb16b93402a0d784306f519f2ade4b2de87a49ce0d629c8827"},"schema_version":"1.0"},"canonical_sha256":"128dfe3a8da17011f69edf9f46a91ad8d6a9fdeec816eab3de6a6c8fc1cbfcb0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:03.318113Z","signature_b64":"Z+tQBJT+7GpazJKP8dZMSve43q9gdCY4Wt17OBgcZg57AnDcK4WZI0pe3AmVwvsywgBqoBe7ihXy7ZE8vdDiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"128dfe3a8da17011f69edf9f46a91ad8d6a9fdeec816eab3de6a6c8fc1cbfcb0","last_reissued_at":"2026-05-18T00:13:03.317521Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:03.317521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.06200","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cvoS4vPomRyN4FEi7r8oW3lzQ8zcbTAq+psaZ3xeb0WgJAHyzM7u4vZTFtms9gpd3YiG2weLNy7Nb0BtYBjQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:08:59.809606Z"},"content_sha256":"6eb177c5db247e960e410542861bdb7119fa2bb3d00018fb395bac8df315b8d6","schema_version":"1.0","event_id":"sha256:6eb177c5db247e960e410542861bdb7119fa2bb3d00018fb395bac8df315b8d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CKG74OUNUFYBD5U636PUNKI23D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eng Siong Chng, Haihua Xu, Lei Xie, Pengcheng Guo","submitted_at":"2018-06-16T07:18:22Z","abstract_excerpt":"In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian Mandarin-English (SEAME) data. We first investigate semi-supervised lexicon learning approach to adapt the canonical lexicon, which is meant to alleviate the heavily accented pronunciation issue within the code-switching conversation of the local area. As a result, the learned lexicon yields improved performance. Furthermore, we attempt to use semi-supervised training to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06200","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:13:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KyiWakoCGCzfn+sPDUW8QYpTsujevMmvLfacvPUS/+1h1eZifnBe49o4ry/ONuhV0BTK8xDawp3b9wTNR1XuAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:08:59.810296Z"},"content_sha256":"698a95cb825aff43d8a142f8d969307c31cfe62913ac21074e2521dfc27643a1","schema_version":"1.0","event_id":"sha256:698a95cb825aff43d8a142f8d969307c31cfe62913ac21074e2521dfc27643a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKG74OUNUFYBD5U636PUNKI23D/bundle.json","state_url":"https://pith.science/pith/CKG74OUNUFYBD5U636PUNKI23D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKG74OUNUFYBD5U636PUNKI23D/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-05T22:08:59Z","links":{"resolver":"https://pith.science/pith/CKG74OUNUFYBD5U636PUNKI23D","bundle":"https://pith.science/pith/CKG74OUNUFYBD5U636PUNKI23D/bundle.json","state":"https://pith.science/pith/CKG74OUNUFYBD5U636PUNKI23D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKG74OUNUFYBD5U636PUNKI23D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CKG74OUNUFYBD5U636PUNKI23D","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":"c267cd9a48012fcb16b93402a0d784306f519f2ade4b2de87a49ce0d629c8827","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-16T07:18:22Z","title_canon_sha256":"48db0a722473fd7a7c1d81b7b6403a9c3ffec7a3a4adad673fc46b83b63fc780"},"schema_version":"1.0","source":{"id":"1806.06200","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.06200","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"arxiv_version","alias_value":"1806.06200v1","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.06200","created_at":"2026-05-18T00:13:03Z"},{"alias_kind":"pith_short_12","alias_value":"CKG74OUNUFYB","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CKG74OUNUFYBD5U6","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CKG74OUN","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:698a95cb825aff43d8a142f8d969307c31cfe62913ac21074e2521dfc27643a1","target":"graph","created_at":"2026-05-18T00:13:03Z","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"},"paper":{"abstract_excerpt":"In this paper, we present our overall efforts to improve the performance of a code-switching speech recognition system using semi-supervised training methods from lexicon learning to acoustic modeling, on the South East Asian Mandarin-English (SEAME) data. We first investigate semi-supervised lexicon learning approach to adapt the canonical lexicon, which is meant to alleviate the heavily accented pronunciation issue within the code-switching conversation of the local area. As a result, the learned lexicon yields improved performance. Furthermore, we attempt to use semi-supervised training to ","authors_text":"Eng Siong Chng, Haihua Xu, Lei Xie, Pengcheng Guo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-16T07:18:22Z","title":"Study of Semi-supervised Approaches to Improving English-Mandarin Code-Switching Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.06200","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":"sha256:6eb177c5db247e960e410542861bdb7119fa2bb3d00018fb395bac8df315b8d6","target":"record","created_at":"2026-05-18T00:13:03Z","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":"c267cd9a48012fcb16b93402a0d784306f519f2ade4b2de87a49ce0d629c8827","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-16T07:18:22Z","title_canon_sha256":"48db0a722473fd7a7c1d81b7b6403a9c3ffec7a3a4adad673fc46b83b63fc780"},"schema_version":"1.0","source":{"id":"1806.06200","kind":"arxiv","version":1}},"canonical_sha256":"128dfe3a8da17011f69edf9f46a91ad8d6a9fdeec816eab3de6a6c8fc1cbfcb0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"128dfe3a8da17011f69edf9f46a91ad8d6a9fdeec816eab3de6a6c8fc1cbfcb0","first_computed_at":"2026-05-18T00:13:03.317521Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:03.317521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z+tQBJT+7GpazJKP8dZMSve43q9gdCY4Wt17OBgcZg57AnDcK4WZI0pe3AmVwvsywgBqoBe7ihXy7ZE8vdDiCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:03.318113Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.06200","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6eb177c5db247e960e410542861bdb7119fa2bb3d00018fb395bac8df315b8d6","sha256:698a95cb825aff43d8a142f8d969307c31cfe62913ac21074e2521dfc27643a1"],"state_sha256":"d48666133cf7875538bd7bc1b4d7adea9efd883ea69ceceb625409254856e7b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jWJG6laoH7APNl7GVytUSZT+Qpc/wk7sbMPuGY7JA23QxlcVDER0oJO5E5CZZNjjF/pqTzlkBFzr6ZAjSEDrBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T22:08:59.814044Z","bundle_sha256":"6d1ce8175d891413f5cde480bdc185f09b77bf675a57d8e868f6cfbf8794eb3a"}}