{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ZNNSXKCRSMVDF4UMTTTZNTOBDY","short_pith_number":"pith:ZNNSXKCR","schema_version":"1.0","canonical_sha256":"cb5b2ba851932a32f28c9ce796cdc11e1943decb3f551c60265576caaa340f9f","source":{"kind":"arxiv","id":"2006.04558","version":8},"attestation_state":"computed","paper":{"title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenxu Hu, Sheng Zhao, Tao Qin, Tie-Yan Liu, Xu Tan, Yi Ren, Zhou Zhao","submitted_at":"2020-06-08T13:05:40Z","abstract_excerpt":"Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is compl"},"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":"2006.04558","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-06-08T13:05:40Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"71b604879a006d7f4f245e7039c4340725b8124174ba702d0521dfd8411714e7","abstract_canon_sha256":"c6028a059f263eb9d300d7a885e80fa9ca57839d088e5826d59440d5ffa4df25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:29.806887Z","signature_b64":"ufx1YbfgClC6F07RsSWXdqX8YxgWnTcapAYew4oXb7rcv1lhADoCDmIhJBc7Ur+7pCkT/ZPomd8gah0ZLP41AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb5b2ba851932a32f28c9ce796cdc11e1943decb3f551c60265576caaa340f9f","last_reissued_at":"2026-07-05T04:46:29.806424Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:29.806424Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FastSpeech 2: Fast and High-Quality End-to-End Text to Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenxu Hu, Sheng Zhao, Tao Qin, Tie-Yan Liu, Xu Tan, Yi Ren, Zhou Zhao","submitted_at":"2020-06-08T13:05:40Z","abstract_excerpt":"Non-autoregressive text to speech (TTS) models such as FastSpeech can synthesize speech significantly faster than previous autoregressive models with comparable quality. The training of FastSpeech model relies on an autoregressive teacher model for duration prediction (to provide more information as input) and knowledge distillation (to simplify the data distribution in output), which can ease the one-to-many mapping problem (i.e., multiple speech variations correspond to the same text) in TTS. However, FastSpeech has several disadvantages: 1) the teacher-student distillation pipeline is compl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.04558","kind":"arxiv","version":8},"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/2006.04558/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":"2006.04558","created_at":"2026-07-05T04:46:29.806488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.04558v8","created_at":"2026-07-05T04:46:29.806488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.04558","created_at":"2026-07-05T04:46:29.806488+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZNNSXKCRSMVD","created_at":"2026-07-05T04:46:29.806488+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZNNSXKCRSMVDF4UM","created_at":"2026-07-05T04:46:29.806488+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZNNSXKCR","created_at":"2026-07-05T04:46:29.806488+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22310","citing_title":"Learning to Evade: Adaptive Attacks on Audio Watermarking","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21457","citing_title":"DisSpeech: Low-Resource Controllable Mandarin Stuttered Speech Synthesis for ASR Augmentation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19209","citing_title":"FineCombo-TTS: Collaborative and Precise Controllable Speech Synthesis Using Text Descriptions and Reference Speech","ref_index":8,"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":160,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30580","citing_title":"MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2505.00409","citing_title":"Perceptual implications of automatic anonymization in pathological speech","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23552","citing_title":"JAM-Flow: Joint Audio-Motion Synthesis with Flow Matching","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20086","citing_title":"OLaPh: Optimal Language Phonemizer","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20657","citing_title":"Intelligent Agents with Emotional Intelligence: Current Trends, Challenges, and Future Prospects","ref_index":140,"is_internal_anchor":false},{"citing_arxiv_id":"2410.06885","citing_title":"F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2507.16632","citing_title":"Step-Audio 2 Technical Report","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2602.22029","citing_title":"MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2406.02430","citing_title":"Seed-TTS: A Family of High-Quality Versatile Speech Generation Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09971","citing_title":"HapticLDM: A Diffusion Model for Text-to-Vibrotactile Generation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01515","citing_title":"MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16056","citing_title":"AST: Adaptive, Seamless, and Training-Free Precise Speech Editing","ref_index":3,"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":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZNNSXKCRSMVDF4UMTTTZNTOBDY","json":"https://pith.science/pith/ZNNSXKCRSMVDF4UMTTTZNTOBDY.json","graph_json":"https://pith.science/api/pith-number/ZNNSXKCRSMVDF4UMTTTZNTOBDY/graph.json","events_json":"https://pith.science/api/pith-number/ZNNSXKCRSMVDF4UMTTTZNTOBDY/events.json","paper":"https://pith.science/paper/ZNNSXKCR"},"agent_actions":{"view_html":"https://pith.science/pith/ZNNSXKCRSMVDF4UMTTTZNTOBDY","download_json":"https://pith.science/pith/ZNNSXKCRSMVDF4UMTTTZNTOBDY.json","view_paper":"https://pith.science/paper/ZNNSXKCR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.04558&json=true","fetch_graph":"https://pith.science/api/pith-number/ZNNSXKCRSMVDF4UMTTTZNTOBDY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZNNSXKCRSMVDF4UMTTTZNTOBDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZNNSXKCRSMVDF4UMTTTZNTOBDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZNNSXKCRSMVDF4UMTTTZNTOBDY/action/storage_attestation","attest_author":"https://pith.science/pith/ZNNSXKCRSMVDF4UMTTTZNTOBDY/action/author_attestation","sign_citation":"https://pith.science/pith/ZNNSXKCRSMVDF4UMTTTZNTOBDY/action/citation_signature","submit_replication":"https://pith.science/pith/ZNNSXKCRSMVDF4UMTTTZNTOBDY/action/replication_record"}},"created_at":"2026-07-05T04:46:29.806488+00:00","updated_at":"2026-07-05T04:46:29.806488+00:00"}