{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WGAGPRBA3RX565XVWVPCRS3O3X","short_pith_number":"pith:WGAGPRBA","schema_version":"1.0","canonical_sha256":"b18067c420dc6fdf76f5b55e28cb6eddc1a70d99b531701e609621917b144e6c","source":{"kind":"arxiv","id":"1812.05253","version":4},"attestation_state":"computed","paper":{"title":"Modeling Multi-speaker Latent Space to Improve Neural TTS: Quick Enrolling New Speaker and Enhancing Premium Voice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Frank Soong, Lei He, Yan Deng","submitted_at":"2018-12-13T03:41:58Z","abstract_excerpt":"Neural TTS has shown it can generate high quality synthesized speech. In this paper, we investigate the multi-speaker latent space to improve neural TTS for adapting the system to new speakers with only several minutes of speech or enhancing a premium voice by utilizing the data from other speakers for richer contextual coverage and better generalization. A multi-speaker neural TTS model is built with the embedded speaker information in both spectral and speaker latent space. The experimental results show that, with less than 5 minutes of training data from a new speaker, the new model can ach"},"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":"1812.05253","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2018-12-13T03:41:58Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"d082f11d8be3fe615d6114db12a6ab53c83d424c358cfca0f8e3d42818eb1e4d","abstract_canon_sha256":"2248611d29b1e133a22eefab588c4bc7ad74b7aff307ad19189701566b160bde"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:00:53.852945Z","signature_b64":"VbXbbRKvumGqQ3Hy0AlOiN2V639LrZWKdpjZj9vDO+2VhRcv8KQ3zq1U2qZG7/8/Y93s6R60/YRZiBFPpHiuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b18067c420dc6fdf76f5b55e28cb6eddc1a70d99b531701e609621917b144e6c","last_reissued_at":"2026-07-05T00:00:53.852389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:00:53.852389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Multi-speaker Latent Space to Improve Neural TTS: Quick Enrolling New Speaker and Enhancing Premium Voice","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Frank Soong, Lei He, Yan Deng","submitted_at":"2018-12-13T03:41:58Z","abstract_excerpt":"Neural TTS has shown it can generate high quality synthesized speech. In this paper, we investigate the multi-speaker latent space to improve neural TTS for adapting the system to new speakers with only several minutes of speech or enhancing a premium voice by utilizing the data from other speakers for richer contextual coverage and better generalization. A multi-speaker neural TTS model is built with the embedded speaker information in both spectral and speaker latent space. The experimental results show that, with less than 5 minutes of training data from a new speaker, the new model can ach"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.05253","kind":"arxiv","version":4},"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/1812.05253/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":"1812.05253","created_at":"2026-07-05T00:00:53.852449+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.05253v4","created_at":"2026-07-05T00:00:53.852449+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.05253","created_at":"2026-07-05T00:00:53.852449+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGAGPRBA3RX5","created_at":"2026-07-05T00:00:53.852449+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGAGPRBA3RX565XV","created_at":"2026-07-05T00:00:53.852449+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGAGPRBA","created_at":"2026-07-05T00:00:53.852449+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/WGAGPRBA3RX565XVWVPCRS3O3X","json":"https://pith.science/pith/WGAGPRBA3RX565XVWVPCRS3O3X.json","graph_json":"https://pith.science/api/pith-number/WGAGPRBA3RX565XVWVPCRS3O3X/graph.json","events_json":"https://pith.science/api/pith-number/WGAGPRBA3RX565XVWVPCRS3O3X/events.json","paper":"https://pith.science/paper/WGAGPRBA"},"agent_actions":{"view_html":"https://pith.science/pith/WGAGPRBA3RX565XVWVPCRS3O3X","download_json":"https://pith.science/pith/WGAGPRBA3RX565XVWVPCRS3O3X.json","view_paper":"https://pith.science/paper/WGAGPRBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.05253&json=true","fetch_graph":"https://pith.science/api/pith-number/WGAGPRBA3RX565XVWVPCRS3O3X/graph.json","fetch_events":"https://pith.science/api/pith-number/WGAGPRBA3RX565XVWVPCRS3O3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGAGPRBA3RX565XVWVPCRS3O3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGAGPRBA3RX565XVWVPCRS3O3X/action/storage_attestation","attest_author":"https://pith.science/pith/WGAGPRBA3RX565XVWVPCRS3O3X/action/author_attestation","sign_citation":"https://pith.science/pith/WGAGPRBA3RX565XVWVPCRS3O3X/action/citation_signature","submit_replication":"https://pith.science/pith/WGAGPRBA3RX565XVWVPCRS3O3X/action/replication_record"}},"created_at":"2026-07-05T00:00:53.852449+00:00","updated_at":"2026-07-05T00:00:53.852449+00:00"}