{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ENRKCBJNZWMRTPD57UEFPIC5VH","short_pith_number":"pith:ENRKCBJN","schema_version":"1.0","canonical_sha256":"2362a1052dcd9919bc7dfd0857a05da9ec590c838b3db998085004b2bed6829e","source":{"kind":"arxiv","id":"2305.13629","version":3},"attestation_state":"computed","paper":{"title":"TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hongfei Xue, Jie Liu, Lei Xie, Peikun Chen, Pengcheng Guo, Qijie Shao","submitted_at":"2023-05-23T02:57:45Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.13629","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2023-05-23T02:57:45Z","cross_cats_sorted":[],"title_canon_sha256":"bf3eec8853042f2f2c8fb3fbc30c7b906a36ecb751d6cb90478a96dff4450e9f","abstract_canon_sha256":"07b72a0a7d9e8506d7465ddb8cf660074d8c2f5c0d66f2757936bce36730e642"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:10.111831Z","signature_b64":"1VpwbEM8F1TDFXRNL8DrDOORj0jyrq2f9NejrACmVoV3RrwJ+uUUlR1a785CCwKY08+psTJxXf/HW10GHhr9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2362a1052dcd9919bc7dfd0857a05da9ec590c838b3db998085004b2bed6829e","last_reissued_at":"2026-07-05T06:58:10.111411Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:10.111411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TranUSR: Phoneme-to-word Transcoder Based Unified Speech Representation Learning for Cross-lingual Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Hongfei Xue, Jie Liu, Lei Xie, Peikun Chen, Pengcheng Guo, Qijie Shao","submitted_at":"2023-05-23T02:57:45Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13629","kind":"arxiv","version":3},"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/2305.13629/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.13629","created_at":"2026-07-05T06:58:10.111473+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13629v3","created_at":"2026-07-05T06:58:10.111473+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13629","created_at":"2026-07-05T06:58:10.111473+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENRKCBJNZWMR","created_at":"2026-07-05T06:58:10.111473+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENRKCBJNZWMRTPD5","created_at":"2026-07-05T06:58:10.111473+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENRKCBJN","created_at":"2026-07-05T06:58:10.111473+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENRKCBJNZWMRTPD57UEFPIC5VH","json":"https://pith.science/pith/ENRKCBJNZWMRTPD57UEFPIC5VH.json","graph_json":"https://pith.science/api/pith-number/ENRKCBJNZWMRTPD57UEFPIC5VH/graph.json","events_json":"https://pith.science/api/pith-number/ENRKCBJNZWMRTPD57UEFPIC5VH/events.json","paper":"https://pith.science/paper/ENRKCBJN"},"agent_actions":{"view_html":"https://pith.science/pith/ENRKCBJNZWMRTPD57UEFPIC5VH","download_json":"https://pith.science/pith/ENRKCBJNZWMRTPD57UEFPIC5VH.json","view_paper":"https://pith.science/paper/ENRKCBJN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13629&json=true","fetch_graph":"https://pith.science/api/pith-number/ENRKCBJNZWMRTPD57UEFPIC5VH/graph.json","fetch_events":"https://pith.science/api/pith-number/ENRKCBJNZWMRTPD57UEFPIC5VH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENRKCBJNZWMRTPD57UEFPIC5VH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENRKCBJNZWMRTPD57UEFPIC5VH/action/storage_attestation","attest_author":"https://pith.science/pith/ENRKCBJNZWMRTPD57UEFPIC5VH/action/author_attestation","sign_citation":"https://pith.science/pith/ENRKCBJNZWMRTPD57UEFPIC5VH/action/citation_signature","submit_replication":"https://pith.science/pith/ENRKCBJNZWMRTPD57UEFPIC5VH/action/replication_record"}},"created_at":"2026-07-05T06:58:10.111473+00:00","updated_at":"2026-07-05T06:58:10.111473+00:00"}