{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LWIIUKEB4RL3MIECHJWYXK6UNT","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":"95a50437c6451fcd6c2a09423cfbd8adb24330086904facc95a580048c10e407","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T10:15:11Z","title_canon_sha256":"054cbe2708395ee5c4ed8c7b77f6052a496df00c341d29575c8271c0f03855af"},"schema_version":"1.0","source":{"id":"2305.11569","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11569","created_at":"2026-07-05T06:11:48Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11569v1","created_at":"2026-07-05T06:11:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11569","created_at":"2026-07-05T06:11:48Z"},{"alias_kind":"pith_short_12","alias_value":"LWIIUKEB4RL3","created_at":"2026-07-05T06:11:48Z"},{"alias_kind":"pith_short_16","alias_value":"LWIIUKEB4RL3MIEC","created_at":"2026-07-05T06:11:48Z"},{"alias_kind":"pith_short_8","alias_value":"LWIIUKEB","created_at":"2026-07-05T06:11:48Z"}],"graph_snapshots":[{"event_id":"sha256:a87cf72ea8a5e462d836b1870996e169a0129ac1dd8a99b1de1ee6fb95064959","target":"graph","created_at":"2026-07-05T06:11:48Z","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/2305.11569/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We improve low-resource ASR by integrating the ideas of multilingual training and self-supervised learning. Concretely, we leverage an International Phonetic Alphabet (IPA) multilingual model to create frame-level pseudo labels for unlabeled speech, and use these pseudo labels to guide hidden-unit BERT (HuBERT) based speech pretraining in a phonetically-informed manner. The experiments on the Multilingual Speech (MLS) Corpus show that the proposed approach consistently outperforms the standard HuBERT on all the target languages. Moreover, on 3 of the 4 languages, comparing to the standard HuBE","authors_text":"Chuanzeng Huang, Ming Tu, Rui Xia, Siyuan Feng, Yuxuan Wang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T10:15:11Z","title":"Language-Universal Phonetic Representation in Multilingual Speech Pretraining for Low-Resource Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11569","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":"sha256:5883e051c55d48f33069a8ccbc0b9db8b793a5c8263299bf63837566250cc747","target":"record","created_at":"2026-07-05T06:11:48Z","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":"95a50437c6451fcd6c2a09423cfbd8adb24330086904facc95a580048c10e407","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-19T10:15:11Z","title_canon_sha256":"054cbe2708395ee5c4ed8c7b77f6052a496df00c341d29575c8271c0f03855af"},"schema_version":"1.0","source":{"id":"2305.11569","kind":"arxiv","version":1}},"canonical_sha256":"5d908a2881e457b620823a6d8babd46ccfa12690f5005c27960f1990b071f109","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d908a2881e457b620823a6d8babd46ccfa12690f5005c27960f1990b071f109","first_computed_at":"2026-07-05T06:11:48.696177Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:48.696177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JoCBTauw8EBfved8XRBYZIODgjG4qvPGkWP+kPKqRX4xfUapmy5OLBBZym6pZYGSLJVgF5tQ4irkIRBCbz2aAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:48.696558Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11569","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5883e051c55d48f33069a8ccbc0b9db8b793a5c8263299bf63837566250cc747","sha256:a87cf72ea8a5e462d836b1870996e169a0129ac1dd8a99b1de1ee6fb95064959"],"state_sha256":"845dbd0cce4b73be9739d6590cc80bad33bb309b87864825ca05ff8a16eeb1c4"}