{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JOOXMZ76XEYWZVICR4W5TPPOZF","short_pith_number":"pith:JOOXMZ76","canonical_record":{"source":{"id":"2110.03504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T14:43:35Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"8b5b9ff06f2a1b4d95a15905da7f23f52fc894f8af3770bbfa1d99561be2f8d6","abstract_canon_sha256":"2e7c8235af33940978fba6efc503cfdb8afb3edff0585ddde9398a46b903462e"},"schema_version":"1.0"},"canonical_sha256":"4b9d7667feb9316cd5028f2dd9bdeec9742b3b9ee223fba69b11d2167136cf29","source":{"kind":"arxiv","id":"2110.03504","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03504","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03504v1","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03504","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"JOOXMZ76XEYW","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"JOOXMZ76XEYWZVIC","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"JOOXMZ76","created_at":"2026-07-05T03:20:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JOOXMZ76XEYWZVICR4W5TPPOZF","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03504","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T14:43:35Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"8b5b9ff06f2a1b4d95a15905da7f23f52fc894f8af3770bbfa1d99561be2f8d6","abstract_canon_sha256":"2e7c8235af33940978fba6efc503cfdb8afb3edff0585ddde9398a46b903462e"},"schema_version":"1.0"},"canonical_sha256":"4b9d7667feb9316cd5028f2dd9bdeec9742b3b9ee223fba69b11d2167136cf29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:43.412403Z","signature_b64":"5CdpMu55l7s+ngaWcagAqrX+WPAhkp7cno+X/PqpDQI3Pff3yUUBF+Ph4RLS9NE3YtC0Vi38x3R2JoxxyXFwBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b9d7667feb9316cd5028f2dd9bdeec9742b3b9ee223fba69b11d2167136cf29","last_reissued_at":"2026-07-05T03:20:43.411928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:43.411928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03504","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":"2026-07-05T03:20:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQhk47d22QfOeyVcQzEURjH7oiU9UK74N8JEQgR9/QgAsCdZicbdyvwJm7nejhBdfdq6qhP+tS6naMmgOWt5Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T23:58:38.071065Z"},"content_sha256":"b91483072a02089f34ac9c92295e2d4d46d8c7326612149bef52d60db19f4b21","schema_version":"1.0","event_id":"sha256:b91483072a02089f34ac9c92295e2d4d46d8c7326612149bef52d60db19f4b21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JOOXMZ76XEYWZVICR4W5TPPOZF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Heng-Jui Chang, Hung-yi Lee, Liang-Hsuan Tseng, Yu-Kuan Fu","submitted_at":"2021-10-07T14:43:35Z","abstract_excerpt":"Code-switching (CS) is common in daily conversations where more than one language is used within a sentence. The difficulties of CS speech recognition lie in alternating languages and the lack of transcribed data. Therefore, this paper uses the recently successful self-supervised learning (SSL) methods to leverage many unlabeled speech data without CS. We show that hidden representations of SSL models offer frame-level language identity even if the models are trained with English speech only. Jointly training CTC and language identification modules with self-supervised speech representations i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03504","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/2110.03504/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":"2026-07-05T03:20:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xSSDNtgN+psYrb1Gz14GxhIlQUdEyJ21dcjoDG3Xhg3td42dTc3zNeLiwK97jRbGQ5tpuJZZ4+62fE+H+L+RDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T23:58:38.071459Z"},"content_sha256":"8261564481c965a755d4888f4fc76be96bd64ef52453da8242dd240c9187b901","schema_version":"1.0","event_id":"sha256:8261564481c965a755d4888f4fc76be96bd64ef52453da8242dd240c9187b901"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JOOXMZ76XEYWZVICR4W5TPPOZF/bundle.json","state_url":"https://pith.science/pith/JOOXMZ76XEYWZVICR4W5TPPOZF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JOOXMZ76XEYWZVICR4W5TPPOZF/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":"2026-07-13T23:58:38Z","links":{"resolver":"https://pith.science/pith/JOOXMZ76XEYWZVICR4W5TPPOZF","bundle":"https://pith.science/pith/JOOXMZ76XEYWZVICR4W5TPPOZF/bundle.json","state":"https://pith.science/pith/JOOXMZ76XEYWZVICR4W5TPPOZF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JOOXMZ76XEYWZVICR4W5TPPOZF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JOOXMZ76XEYWZVICR4W5TPPOZF","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":"2e7c8235af33940978fba6efc503cfdb8afb3edff0585ddde9398a46b903462e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T14:43:35Z","title_canon_sha256":"8b5b9ff06f2a1b4d95a15905da7f23f52fc894f8af3770bbfa1d99561be2f8d6"},"schema_version":"1.0","source":{"id":"2110.03504","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03504","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03504v1","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03504","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"pith_short_12","alias_value":"JOOXMZ76XEYW","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"pith_short_16","alias_value":"JOOXMZ76XEYWZVIC","created_at":"2026-07-05T03:20:43Z"},{"alias_kind":"pith_short_8","alias_value":"JOOXMZ76","created_at":"2026-07-05T03:20:43Z"}],"graph_snapshots":[{"event_id":"sha256:8261564481c965a755d4888f4fc76be96bd64ef52453da8242dd240c9187b901","target":"graph","created_at":"2026-07-05T03:20:43Z","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/2110.03504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Code-switching (CS) is common in daily conversations where more than one language is used within a sentence. The difficulties of CS speech recognition lie in alternating languages and the lack of transcribed data. Therefore, this paper uses the recently successful self-supervised learning (SSL) methods to leverage many unlabeled speech data without CS. We show that hidden representations of SSL models offer frame-level language identity even if the models are trained with English speech only. Jointly training CTC and language identification modules with self-supervised speech representations i","authors_text":"Heng-Jui Chang, Hung-yi Lee, Liang-Hsuan Tseng, Yu-Kuan Fu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T14:43:35Z","title":"Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03504","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:b91483072a02089f34ac9c92295e2d4d46d8c7326612149bef52d60db19f4b21","target":"record","created_at":"2026-07-05T03:20:43Z","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":"2e7c8235af33940978fba6efc503cfdb8afb3edff0585ddde9398a46b903462e","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-07T14:43:35Z","title_canon_sha256":"8b5b9ff06f2a1b4d95a15905da7f23f52fc894f8af3770bbfa1d99561be2f8d6"},"schema_version":"1.0","source":{"id":"2110.03504","kind":"arxiv","version":1}},"canonical_sha256":"4b9d7667feb9316cd5028f2dd9bdeec9742b3b9ee223fba69b11d2167136cf29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b9d7667feb9316cd5028f2dd9bdeec9742b3b9ee223fba69b11d2167136cf29","first_computed_at":"2026-07-05T03:20:43.411928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:43.411928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5CdpMu55l7s+ngaWcagAqrX+WPAhkp7cno+X/PqpDQI3Pff3yUUBF+Ph4RLS9NE3YtC0Vi38x3R2JoxxyXFwBg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:43.412403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03504","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b91483072a02089f34ac9c92295e2d4d46d8c7326612149bef52d60db19f4b21","sha256:8261564481c965a755d4888f4fc76be96bd64ef52453da8242dd240c9187b901"],"state_sha256":"c243a0b9cd7fa0e2fe37eae9d1b77578a5aef9b1fefad82aafcefd0a5a267f21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F9yp1+VCYSn0XZX2yHz1hQWzORzerMSXr2dXFR6YRP8BigVTFI+UASJ9+dDPLmWkQjS/WLorQHvADM28CoVNDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T23:58:38.074624Z","bundle_sha256":"3ceb8dbd993fbe010056930e40b476bf98bb1c168f28ca9f7cec1bbc4c9aa16f"}}