{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E4SNF44QOWMJRKYTIVQ7WJ7QQE","short_pith_number":"pith:E4SNF44Q","schema_version":"1.0","canonical_sha256":"2724d2f390759898ab134561fb27f0811f4b495b44a35f42436c8a983b613a72","source":{"kind":"arxiv","id":"2106.15561","version":3},"attestation_state":"computed","paper":{"title":"A Survey on Neural Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Frank Soong, Tao Qin, Tie-Yan Liu, Xu Tan","submitted_at":"2021-06-29T16:50:51Z","abstract_excerpt":"Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural speech given text, is a hot research topic in speech, language, and machine learning communities and has broad applications in the industry. As the development of deep learning and artificial intelligence, neural network-based TTS has significantly improved the quality of synthesized speech in recent years. In this paper, we conduct a comprehensive survey on neural TTS, aiming to provide a good understanding of current research and future trends. We focus on the key components in neural TTS, including "},"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":"2106.15561","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-06-29T16:50:51Z","cross_cats_sorted":["cs.CL","cs.LG","cs.MM","cs.SD"],"title_canon_sha256":"a5be49861ab9bf40131a71203e9a18d8014abe58b15e9abf286690bc89ad588b","abstract_canon_sha256":"26abbed34cabcd209a2ef26701ba5543b7b272c3110ed27e563ea2f5594b0fb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:09.967010Z","signature_b64":"ScTEyBjYqBlQ5z/EqVEVUUhhFMQJLV8iJnDq4f2nd/tZhV7NgFPebcV3qpYWSHyMLNaqT42FdHFffEHeGEW1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2724d2f390759898ab134561fb27f0811f4b495b44a35f42436c8a983b613a72","last_reissued_at":"2026-07-05T03:00:09.966542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:09.966542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Neural Speech Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.MM","cs.SD"],"primary_cat":"eess.AS","authors_text":"Frank Soong, Tao Qin, Tie-Yan Liu, Xu Tan","submitted_at":"2021-06-29T16:50:51Z","abstract_excerpt":"Text to speech (TTS), or speech synthesis, which aims to synthesize intelligible and natural speech given text, is a hot research topic in speech, language, and machine learning communities and has broad applications in the industry. As the development of deep learning and artificial intelligence, neural network-based TTS has significantly improved the quality of synthesized speech in recent years. In this paper, we conduct a comprehensive survey on neural TTS, aiming to provide a good understanding of current research and future trends. We focus on the key components in neural TTS, including "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.15561","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/2106.15561/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":"2106.15561","created_at":"2026-07-05T03:00:09.966604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.15561v3","created_at":"2026-07-05T03:00:09.966604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.15561","created_at":"2026-07-05T03:00:09.966604+00:00"},{"alias_kind":"pith_short_12","alias_value":"E4SNF44QOWMJ","created_at":"2026-07-05T03:00:09.966604+00:00"},{"alias_kind":"pith_short_16","alias_value":"E4SNF44QOWMJRKYT","created_at":"2026-07-05T03:00:09.966604+00:00"},{"alias_kind":"pith_short_8","alias_value":"E4SNF44Q","created_at":"2026-07-05T03:00:09.966604+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22811","citing_title":"Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21457","citing_title":"DisSpeech: Low-Resource Controllable Mandarin Stuttered Speech Synthesis for ASR Augmentation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09295","citing_title":"N\\\"ushuVoice: Reviving the Voice of Endangered N\\\"ushu with Pitch-Aware Text-to-Speech","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2301.02111","citing_title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26136","citing_title":"One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02374","citing_title":"Evaluating Generalization and Robustness in Russian Anti-Spoofing: The RuASD Initiative","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06901","citing_title":"XR-CareerAssist: An Immersive Platform for Personalised Career Guidance Leveraging Extended Reality and Multimodal AI","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07241","citing_title":"Asymmetric Phase Coding Audio Watermarking","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06901","citing_title":"XR-CareerAssist: An Immersive Platform for Personalised Career Guidance Leveraging Extended Reality and Multimodal AI","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00861","citing_title":"Voice Mapping of Text-to-Speech Systems: A Metric-Based Approach for Voice Quality Assessment","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19949","citing_title":"Indic-CodecFake meets SATYAM: Towards Detecting Neural Audio Codec Synthesized Speech Deepfakes in Indic Languages","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E4SNF44QOWMJRKYTIVQ7WJ7QQE","json":"https://pith.science/pith/E4SNF44QOWMJRKYTIVQ7WJ7QQE.json","graph_json":"https://pith.science/api/pith-number/E4SNF44QOWMJRKYTIVQ7WJ7QQE/graph.json","events_json":"https://pith.science/api/pith-number/E4SNF44QOWMJRKYTIVQ7WJ7QQE/events.json","paper":"https://pith.science/paper/E4SNF44Q"},"agent_actions":{"view_html":"https://pith.science/pith/E4SNF44QOWMJRKYTIVQ7WJ7QQE","download_json":"https://pith.science/pith/E4SNF44QOWMJRKYTIVQ7WJ7QQE.json","view_paper":"https://pith.science/paper/E4SNF44Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.15561&json=true","fetch_graph":"https://pith.science/api/pith-number/E4SNF44QOWMJRKYTIVQ7WJ7QQE/graph.json","fetch_events":"https://pith.science/api/pith-number/E4SNF44QOWMJRKYTIVQ7WJ7QQE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E4SNF44QOWMJRKYTIVQ7WJ7QQE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E4SNF44QOWMJRKYTIVQ7WJ7QQE/action/storage_attestation","attest_author":"https://pith.science/pith/E4SNF44QOWMJRKYTIVQ7WJ7QQE/action/author_attestation","sign_citation":"https://pith.science/pith/E4SNF44QOWMJRKYTIVQ7WJ7QQE/action/citation_signature","submit_replication":"https://pith.science/pith/E4SNF44QOWMJRKYTIVQ7WJ7QQE/action/replication_record"}},"created_at":"2026-07-05T03:00:09.966604+00:00","updated_at":"2026-07-05T03:00:09.966604+00:00"}