{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:XOMZZV76FV4C3X4VBP7AHKTR7P","short_pith_number":"pith:XOMZZV76","schema_version":"1.0","canonical_sha256":"bb999cd7fe2d782ddf950bfe03aa71fbda95f4d7065ddd5543ed0e8a6e247a0d","source":{"kind":"arxiv","id":"2101.07597","version":2},"attestation_state":"computed","paper":{"title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chengyi Wang, Furu Wei, Kenichi Kumatani, Michael Zeng, Shujie Liu, Xuedong Huang, Yao Qian, Yu Wu","submitted_at":"2021-01-19T12:53:43Z","abstract_excerpt":"In this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised learning are conducted in a multi-task learning manner. The resultant representations can capture information more correlated with phonetic structures and improve the generalization across languages and domains. We evaluate the effectiveness of UniSpeech for cross-lingual representation learning on public CommonVoice corpus. The results show that UniSpeech out"},"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":"2101.07597","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-19T12:53:43Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"d7dcc7c631cf661ed5faf38f6a576aabcef6b7655491fde923fce4c230a3f0c1","abstract_canon_sha256":"cf44989acd58cb0ce419ae57d6a2cb6486a520c707f5ed82509b89713c020d9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:58.732657Z","signature_b64":"eu63ISoTGqMWYeCFMQSanmzTkwKCfcydTDm0+l0XcDFfVNkLPmQubH0HBfKvoqgcT64GdLu+Byf3Isz8tpmoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb999cd7fe2d782ddf950bfe03aa71fbda95f4d7065ddd5543ed0e8a6e247a0d","last_reissued_at":"2026-07-05T02:47:58.732168Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:58.732168Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniSpeech: Unified Speech Representation Learning with Labeled and Unlabeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chengyi Wang, Furu Wei, Kenichi Kumatani, Michael Zeng, Shujie Liu, Xuedong Huang, Yao Qian, Yu Wu","submitted_at":"2021-01-19T12:53:43Z","abstract_excerpt":"In this paper, we propose a unified pre-training approach called UniSpeech to learn speech representations with both unlabeled and labeled data, in which supervised phonetic CTC learning and phonetically-aware contrastive self-supervised learning are conducted in a multi-task learning manner. The resultant representations can capture information more correlated with phonetic structures and improve the generalization across languages and domains. We evaluate the effectiveness of UniSpeech for cross-lingual representation learning on public CommonVoice corpus. The results show that UniSpeech out"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.07597","kind":"arxiv","version":2},"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/2101.07597/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":"2101.07597","created_at":"2026-07-05T02:47:58.732220+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.07597v2","created_at":"2026-07-05T02:47:58.732220+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.07597","created_at":"2026-07-05T02:47:58.732220+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOMZZV76FV4C","created_at":"2026-07-05T02:47:58.732220+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOMZZV76FV4C3X4V","created_at":"2026-07-05T02:47:58.732220+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOMZZV76","created_at":"2026-07-05T02:47:58.732220+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12145","citing_title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12145","citing_title":"Cross-Modal-Domain Generalization Through Semantically Aligned Discrete Representations","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOMZZV76FV4C3X4VBP7AHKTR7P","json":"https://pith.science/pith/XOMZZV76FV4C3X4VBP7AHKTR7P.json","graph_json":"https://pith.science/api/pith-number/XOMZZV76FV4C3X4VBP7AHKTR7P/graph.json","events_json":"https://pith.science/api/pith-number/XOMZZV76FV4C3X4VBP7AHKTR7P/events.json","paper":"https://pith.science/paper/XOMZZV76"},"agent_actions":{"view_html":"https://pith.science/pith/XOMZZV76FV4C3X4VBP7AHKTR7P","download_json":"https://pith.science/pith/XOMZZV76FV4C3X4VBP7AHKTR7P.json","view_paper":"https://pith.science/paper/XOMZZV76","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.07597&json=true","fetch_graph":"https://pith.science/api/pith-number/XOMZZV76FV4C3X4VBP7AHKTR7P/graph.json","fetch_events":"https://pith.science/api/pith-number/XOMZZV76FV4C3X4VBP7AHKTR7P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOMZZV76FV4C3X4VBP7AHKTR7P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOMZZV76FV4C3X4VBP7AHKTR7P/action/storage_attestation","attest_author":"https://pith.science/pith/XOMZZV76FV4C3X4VBP7AHKTR7P/action/author_attestation","sign_citation":"https://pith.science/pith/XOMZZV76FV4C3X4VBP7AHKTR7P/action/citation_signature","submit_replication":"https://pith.science/pith/XOMZZV76FV4C3X4VBP7AHKTR7P/action/replication_record"}},"created_at":"2026-07-05T02:47:58.732220+00:00","updated_at":"2026-07-05T02:47:58.732220+00:00"}