{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OONNZTBWRUI7BAQEHOSZ5O7ST7","short_pith_number":"pith:OONNZTBW","canonical_record":{"source":{"id":"2303.10949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-20T09:13:27Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"f22af2a6a8f5b0aac3cd2a8c22ceea85b68f55dfcc14943a14c3d3b2166b9018","abstract_canon_sha256":"ce41c71dbd87923c4761e51820e65fb1f1bec368ef0dfdb6e652eb9d13807bfe"},"schema_version":"1.0"},"canonical_sha256":"739adccc368d11f082043ba59ebbf29fc4777650a5e3e48dfa2d2515e64e407f","source":{"kind":"arxiv","id":"2303.10949","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.10949","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"arxiv_version","alias_value":"2303.10949v1","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10949","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"pith_short_12","alias_value":"OONNZTBWRUI7","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"pith_short_16","alias_value":"OONNZTBWRUI7BAQE","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"pith_short_8","alias_value":"OONNZTBW","created_at":"2026-07-05T05:52:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OONNZTBWRUI7BAQEHOSZ5O7ST7","target":"record","payload":{"canonical_record":{"source":{"id":"2303.10949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-20T09:13:27Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"f22af2a6a8f5b0aac3cd2a8c22ceea85b68f55dfcc14943a14c3d3b2166b9018","abstract_canon_sha256":"ce41c71dbd87923c4761e51820e65fb1f1bec368ef0dfdb6e652eb9d13807bfe"},"schema_version":"1.0"},"canonical_sha256":"739adccc368d11f082043ba59ebbf29fc4777650a5e3e48dfa2d2515e64e407f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:38.552483Z","signature_b64":"V6x8rloO5N3Lg/CT8rVt0JLLbOT7i0MUaZ3+GiltqAWrfplj0vIZ+3ApzuSeR5N5+yjPxMWS6nQZzhvKy5fqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"739adccc368d11f082043ba59ebbf29fc4777650a5e3e48dfa2d2515e64e407f","last_reissued_at":"2026-07-05T05:52:38.552123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:38.552123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.10949","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":"2026-07-05T05:52:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rLFpHaNSFAOE9s22e9rkCHtoW32iJjBet4L9GLRJlBJuOJze8HFn1ErczUof4/9iCtZpxDbtfXVpPnP+9JJ4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:02:41.447965Z"},"content_sha256":"4cdb36ff6b3b4f9d18e7b7939bfcc4fc819214966f9d79412d9cebff54855f0b","schema_version":"1.0","event_id":"sha256:4cdb36ff6b3b4f9d18e7b7939bfcc4fc819214966f9d79412d9cebff54855f0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OONNZTBWRUI7BAQEHOSZ5O7ST7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Code-Switching Text Generation and Injection in Mandarin-English ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Edward Lin, Haibin Yu, Linquan Liu, Ma Jin, Michael Zeng, Shujie Liu, Yanmin Qian, Yao Qian, Yu Shi, Yuxuan Hu","submitted_at":"2023-03-20T09:13:27Z","abstract_excerpt":"Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of data. In this study, we investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T), in Mandarin-English code-switching speech recognition. We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10949","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/2303.10949/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:52:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C/51M19epd/QX22/P6AfbGDcwry3RVX398KhWTS6c9Wii/ZvhNyh5L/EB3fgX8/qmqU6tpQcDHMN3o0nRwiNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:02:41.448884Z"},"content_sha256":"8028a3299bccc1ca63e3eb8da899d05742e18d47b6b4185558a0df221356b915","schema_version":"1.0","event_id":"sha256:8028a3299bccc1ca63e3eb8da899d05742e18d47b6b4185558a0df221356b915"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OONNZTBWRUI7BAQEHOSZ5O7ST7/bundle.json","state_url":"https://pith.science/pith/OONNZTBWRUI7BAQEHOSZ5O7ST7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OONNZTBWRUI7BAQEHOSZ5O7ST7/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":"2026-08-04T23:02:41Z","links":{"resolver":"https://pith.science/pith/OONNZTBWRUI7BAQEHOSZ5O7ST7","bundle":"https://pith.science/pith/OONNZTBWRUI7BAQEHOSZ5O7ST7/bundle.json","state":"https://pith.science/pith/OONNZTBWRUI7BAQEHOSZ5O7ST7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OONNZTBWRUI7BAQEHOSZ5O7ST7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OONNZTBWRUI7BAQEHOSZ5O7ST7","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":"ce41c71dbd87923c4761e51820e65fb1f1bec368ef0dfdb6e652eb9d13807bfe","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-20T09:13:27Z","title_canon_sha256":"f22af2a6a8f5b0aac3cd2a8c22ceea85b68f55dfcc14943a14c3d3b2166b9018"},"schema_version":"1.0","source":{"id":"2303.10949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.10949","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"arxiv_version","alias_value":"2303.10949v1","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.10949","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"pith_short_12","alias_value":"OONNZTBWRUI7","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"pith_short_16","alias_value":"OONNZTBWRUI7BAQE","created_at":"2026-07-05T05:52:38Z"},{"alias_kind":"pith_short_8","alias_value":"OONNZTBW","created_at":"2026-07-05T05:52:38Z"}],"graph_snapshots":[{"event_id":"sha256:8028a3299bccc1ca63e3eb8da899d05742e18d47b6b4185558a0df221356b915","target":"graph","created_at":"2026-07-05T05:52:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.10949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-switching speech refers to a means of expression by mixing two or more languages within a single utterance. Automatic Speech Recognition (ASR) with End-to-End (E2E) modeling for such speech can be a challenging task due to the lack of data. In this study, we investigate text generation and injection for improving the performance of an industry commonly-used streaming model, Transformer-Transducer (T-T), in Mandarin-English code-switching speech recognition. We first propose a strategy to generate code-switching text data and then investigate injecting generated text into T-T model explici","authors_text":"Edward Lin, Haibin Yu, Linquan Liu, Ma Jin, Michael Zeng, Shujie Liu, Yanmin Qian, Yao Qian, Yu Shi, Yuxuan Hu","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-20T09:13:27Z","title":"Code-Switching Text Generation and Injection in Mandarin-English ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.10949","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":"sha256:4cdb36ff6b3b4f9d18e7b7939bfcc4fc819214966f9d79412d9cebff54855f0b","target":"record","created_at":"2026-07-05T05:52:38Z","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":"ce41c71dbd87923c4761e51820e65fb1f1bec368ef0dfdb6e652eb9d13807bfe","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-03-20T09:13:27Z","title_canon_sha256":"f22af2a6a8f5b0aac3cd2a8c22ceea85b68f55dfcc14943a14c3d3b2166b9018"},"schema_version":"1.0","source":{"id":"2303.10949","kind":"arxiv","version":1}},"canonical_sha256":"739adccc368d11f082043ba59ebbf29fc4777650a5e3e48dfa2d2515e64e407f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"739adccc368d11f082043ba59ebbf29fc4777650a5e3e48dfa2d2515e64e407f","first_computed_at":"2026-07-05T05:52:38.552123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:52:38.552123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V6x8rloO5N3Lg/CT8rVt0JLLbOT7i0MUaZ3+GiltqAWrfplj0vIZ+3ApzuSeR5N5+yjPxMWS6nQZzhvKy5fqCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:52:38.552483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.10949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cdb36ff6b3b4f9d18e7b7939bfcc4fc819214966f9d79412d9cebff54855f0b","sha256:8028a3299bccc1ca63e3eb8da899d05742e18d47b6b4185558a0df221356b915"],"state_sha256":"422c3929394409673b06d232940d6faa4376f76f621665914ab7237fb4285d90"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6L0cTuNG4Aj6a3UXmINolJjbwitLEKNurpi3JzCCP7P3h5qU0W+0No7asvv+aEPBRFQws1HdMXm1AG4KBA1MCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:02:41.454367Z","bundle_sha256":"c28db93006b7dbd6ef5b4c2fc605eb45964a2ae91a51cac81f564029b900517a"}}