{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IOYNYGJQQMFP4C6FFR62FBKN4S","short_pith_number":"pith:IOYNYGJQ","schema_version":"1.0","canonical_sha256":"43b0dc1930830afe0bc52c7da2854de4b0415969203f82766814a20c6fd56480","source":{"kind":"arxiv","id":"2303.05322","version":1},"attestation_state":"computed","paper":{"title":"Improving Few-Shot Learning for Talking Face System with TTS Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Yu, Qi Chen, Qu Lu, Tao Liu, Xie Chen, Xu Tan, Ziyang Ma","submitted_at":"2023-03-09T15:13:46Z","abstract_excerpt":"Audio-driven talking face has attracted broad interest from academia and industry recently. However, data acquisition and labeling in audio-driven talking face are labor-intensive and costly. The lack of data resource results in poor synthesis effect. To alleviate this issue, we propose to use TTS (Text-To-Speech) for data augmentation to improve few-shot ability of the talking face system. The misalignment problem brought by the TTS audio is solved with the introduction of soft-DTW, which is first adopted in the talking face task. Moreover, features extracted by HuBERT are explored to utilize"},"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":"2303.05322","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-03-09T15:13:46Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"c70abcd5c75d266cc37cc04ee9922fde7b62d2e5fa7d97b82f339b3f9314ceb9","abstract_canon_sha256":"5ece34649608b198e531b5f501a5b60048c88aaaa7c4f60823db91e6d953bce9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:39.543557Z","signature_b64":"ZdKPdMTvQ1TcWj5daLomnOnk7vZWSEKSPweqygaUiZ4HCr4vLKiNQeNG9HarXavvQCC1uxhx8wvbo21Qv5L2DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43b0dc1930830afe0bc52c7da2854de4b0415969203f82766814a20c6fd56480","last_reissued_at":"2026-07-05T05:49:39.543144Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:39.543144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Few-Shot Learning for Talking Face System with TTS Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Kai Yu, Qi Chen, Qu Lu, Tao Liu, Xie Chen, Xu Tan, Ziyang Ma","submitted_at":"2023-03-09T15:13:46Z","abstract_excerpt":"Audio-driven talking face has attracted broad interest from academia and industry recently. However, data acquisition and labeling in audio-driven talking face are labor-intensive and costly. The lack of data resource results in poor synthesis effect. To alleviate this issue, we propose to use TTS (Text-To-Speech) for data augmentation to improve few-shot ability of the talking face system. The misalignment problem brought by the TTS audio is solved with the introduction of soft-DTW, which is first adopted in the talking face task. Moreover, features extracted by HuBERT are explored to utilize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.05322","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/2303.05322/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":"2303.05322","created_at":"2026-07-05T05:49:39.543201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.05322v1","created_at":"2026-07-05T05:49:39.543201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.05322","created_at":"2026-07-05T05:49:39.543201+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOYNYGJQQMFP","created_at":"2026-07-05T05:49:39.543201+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOYNYGJQQMFP4C6F","created_at":"2026-07-05T05:49:39.543201+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOYNYGJQ","created_at":"2026-07-05T05:49:39.543201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09111","citing_title":"PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IOYNYGJQQMFP4C6FFR62FBKN4S","json":"https://pith.science/pith/IOYNYGJQQMFP4C6FFR62FBKN4S.json","graph_json":"https://pith.science/api/pith-number/IOYNYGJQQMFP4C6FFR62FBKN4S/graph.json","events_json":"https://pith.science/api/pith-number/IOYNYGJQQMFP4C6FFR62FBKN4S/events.json","paper":"https://pith.science/paper/IOYNYGJQ"},"agent_actions":{"view_html":"https://pith.science/pith/IOYNYGJQQMFP4C6FFR62FBKN4S","download_json":"https://pith.science/pith/IOYNYGJQQMFP4C6FFR62FBKN4S.json","view_paper":"https://pith.science/paper/IOYNYGJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.05322&json=true","fetch_graph":"https://pith.science/api/pith-number/IOYNYGJQQMFP4C6FFR62FBKN4S/graph.json","fetch_events":"https://pith.science/api/pith-number/IOYNYGJQQMFP4C6FFR62FBKN4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOYNYGJQQMFP4C6FFR62FBKN4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOYNYGJQQMFP4C6FFR62FBKN4S/action/storage_attestation","attest_author":"https://pith.science/pith/IOYNYGJQQMFP4C6FFR62FBKN4S/action/author_attestation","sign_citation":"https://pith.science/pith/IOYNYGJQQMFP4C6FFR62FBKN4S/action/citation_signature","submit_replication":"https://pith.science/pith/IOYNYGJQQMFP4C6FFR62FBKN4S/action/replication_record"}},"created_at":"2026-07-05T05:49:39.543201+00:00","updated_at":"2026-07-05T05:49:39.543201+00:00"}