{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HVYHFAQKRD6QYBULZYFG5R45RT","short_pith_number":"pith:HVYHFAQK","schema_version":"1.0","canonical_sha256":"3d7072820a88fd0c068bce0a6ec79d8ce4c83bed971c54f82564e944eff20a39","source":{"kind":"arxiv","id":"2103.00993","version":1},"attestation_state":"computed","paper":{"title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bohan Li, Mingjian Chen, Sheng Zhao, Tao Qin, Tie-Yan Liu, Xu Tan, Yanqing Liu","submitted_at":"2021-03-01T13:28:59Z","abstract_excerpt":"Custom voice, a specific text to speech (TTS) service in commercial speech platforms, aims to adapt a source TTS model to synthesize personal voice for a target speaker using few speech data. Custom voice presents two unique challenges for TTS adaptation: 1) to support diverse customers, the adaptation model needs to handle diverse acoustic conditions that could be very different from source speech data, and 2) to support a large number of customers, the adaptation parameters need to be small enough for each target speaker to reduce memory usage while maintaining high voice quality. In this wo"},"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":"2103.00993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-03-01T13:28:59Z","cross_cats_sorted":["cs.AI","cs.CL","cs.SD"],"title_canon_sha256":"2c8324e38298e310e5352147501076eb5fdaa0eb5c8fadc71020698209fdf6df","abstract_canon_sha256":"b013788a6d07c1afff4edc1b240b8f8d2b72d1c160116353d28f2df7870de364"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:19:11.680913Z","signature_b64":"93N5JC8tAxAeCPGDqy6d9kcZHyf2WfCdpi+mT4qoThZa1yoeumY+cjsdAmH2FWbwzj4fiSnjml6R83vpLPNbBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d7072820a88fd0c068bce0a6ec79d8ce4c83bed971c54f82564e944eff20a39","last_reissued_at":"2026-07-05T02:19:11.680500Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:19:11.680500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaSpeech: Adaptive Text to Speech for Custom Voice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Bohan Li, Mingjian Chen, Sheng Zhao, Tao Qin, Tie-Yan Liu, Xu Tan, Yanqing Liu","submitted_at":"2021-03-01T13:28:59Z","abstract_excerpt":"Custom voice, a specific text to speech (TTS) service in commercial speech platforms, aims to adapt a source TTS model to synthesize personal voice for a target speaker using few speech data. Custom voice presents two unique challenges for TTS adaptation: 1) to support diverse customers, the adaptation model needs to handle diverse acoustic conditions that could be very different from source speech data, and 2) to support a large number of customers, the adaptation parameters need to be small enough for each target speaker to reduce memory usage while maintaining high voice quality. In this wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00993","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/2103.00993/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":"2103.00993","created_at":"2026-07-05T02:19:11.680560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.00993v1","created_at":"2026-07-05T02:19:11.680560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00993","created_at":"2026-07-05T02:19:11.680560+00:00"},{"alias_kind":"pith_short_12","alias_value":"HVYHFAQKRD6Q","created_at":"2026-07-05T02:19:11.680560+00:00"},{"alias_kind":"pith_short_16","alias_value":"HVYHFAQKRD6QYBUL","created_at":"2026-07-05T02:19:11.680560+00:00"},{"alias_kind":"pith_short_8","alias_value":"HVYHFAQK","created_at":"2026-07-05T02:19:11.680560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.17690","citing_title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HVYHFAQKRD6QYBULZYFG5R45RT","json":"https://pith.science/pith/HVYHFAQKRD6QYBULZYFG5R45RT.json","graph_json":"https://pith.science/api/pith-number/HVYHFAQKRD6QYBULZYFG5R45RT/graph.json","events_json":"https://pith.science/api/pith-number/HVYHFAQKRD6QYBULZYFG5R45RT/events.json","paper":"https://pith.science/paper/HVYHFAQK"},"agent_actions":{"view_html":"https://pith.science/pith/HVYHFAQKRD6QYBULZYFG5R45RT","download_json":"https://pith.science/pith/HVYHFAQKRD6QYBULZYFG5R45RT.json","view_paper":"https://pith.science/paper/HVYHFAQK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.00993&json=true","fetch_graph":"https://pith.science/api/pith-number/HVYHFAQKRD6QYBULZYFG5R45RT/graph.json","fetch_events":"https://pith.science/api/pith-number/HVYHFAQKRD6QYBULZYFG5R45RT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HVYHFAQKRD6QYBULZYFG5R45RT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HVYHFAQKRD6QYBULZYFG5R45RT/action/storage_attestation","attest_author":"https://pith.science/pith/HVYHFAQKRD6QYBULZYFG5R45RT/action/author_attestation","sign_citation":"https://pith.science/pith/HVYHFAQKRD6QYBULZYFG5R45RT/action/citation_signature","submit_replication":"https://pith.science/pith/HVYHFAQKRD6QYBULZYFG5R45RT/action/replication_record"}},"created_at":"2026-07-05T02:19:11.680560+00:00","updated_at":"2026-07-05T02:19:11.680560+00:00"}