{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ENRKCBJNZWMRTPD57UEFPIC5VH","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":"07b72a0a7d9e8506d7465ddb8cf660074d8c2f5c0d66f2757936bce36730e642","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-23T02:57:45Z","title_canon_sha256":"bf3eec8853042f2f2c8fb3fbc30c7b906a36ecb751d6cb90478a96dff4450e9f"},"schema_version":"1.0","source":{"id":"2305.13629","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13629","created_at":"2026-07-05T06:58:10Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13629v3","created_at":"2026-07-05T06:58:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13629","created_at":"2026-07-05T06:58:10Z"},{"alias_kind":"pith_short_12","alias_value":"ENRKCBJNZWMR","created_at":"2026-07-05T06:58:10Z"},{"alias_kind":"pith_short_16","alias_value":"ENRKCBJNZWMRTPD5","created_at":"2026-07-05T06:58:10Z"},{"alias_kind":"pith_short_8","alias_value":"ENRKCBJN","created_at":"2026-07-05T06:58:10Z"}],"graph_snapshots":[{"event_id":"sha256:ff3b175f41551af4da2fb4f36cdf881542f62b343742263ae1c7d0fa6ddfc34b","target":"graph","created_at":"2026-07-05T06:58:10Z","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/2305.13629/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"UniSpeech has achieved superior performance in cross-lingual automatic speech recognition (ASR) by explicitly aligning latent representations to phoneme units using multi-task self-supervised learning. While the learned representations transfer well from high-resource to low-resource languages, predicting words directly from these phonetic representations in downstream ASR is challenging. In this paper, we propose TranUSR, a two-stage model comprising a pre-trained UniData2vec and a phoneme-to-word Transcoder. Different from UniSpeech, UniData2vec replaces the quantized discrete representation","authors_text":"Hongfei Xue, Jie Liu, Lei Xie, Peikun Chen, Pengcheng Guo, Qijie Shao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-23T02:57:45Z","title":"TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13629","kind":"arxiv","version":3},"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":"sha256:001d781e9b3b42183ed7c7a354d72bc75b404d6821e9fbf5b707516d94ecb2a0","target":"record","created_at":"2026-07-05T06:58:10Z","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":"07b72a0a7d9e8506d7465ddb8cf660074d8c2f5c0d66f2757936bce36730e642","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-23T02:57:45Z","title_canon_sha256":"bf3eec8853042f2f2c8fb3fbc30c7b906a36ecb751d6cb90478a96dff4450e9f"},"schema_version":"1.0","source":{"id":"2305.13629","kind":"arxiv","version":3}},"canonical_sha256":"2362a1052dcd9919bc7dfd0857a05da9ec590c838b3db998085004b2bed6829e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2362a1052dcd9919bc7dfd0857a05da9ec590c838b3db998085004b2bed6829e","first_computed_at":"2026-07-05T06:58:10.111411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:10.111411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1VpwbEM8F1TDFXRNL8DrDOORj0jyrq2f9NejrACmVoV3RrwJ+uUUlR1a785CCwKY08+psTJxXf/HW10GHhr9Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:10.111831Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13629","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:001d781e9b3b42183ed7c7a354d72bc75b404d6821e9fbf5b707516d94ecb2a0","sha256:ff3b175f41551af4da2fb4f36cdf881542f62b343742263ae1c7d0fa6ddfc34b"],"state_sha256":"7a2f3a8dcf34757cca10045dbb569bd02df3aa701b115f90886788905371740f"}