{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/naturalspeech-end-to-end-text-to-speech","title":"NaturalSpeech: End-to-End Text to Speech Synthesis with Human-Level Quality","arxiv_id":"2205.04421","date":"2022-05-09","proceeding":null,"authors":["Xu Tan","Jiawei Chen","Haohe Liu","Jian Cong","Chen Zhang","Yanqing Liu","Xi Wang","Yichong Leng","YuanHao Yi","Lei He","Frank Soong","Tao Qin","Sheng Zhao","Tie-Yan Liu"],"abstract":"Text to speech (TTS) has made rapid progress in both academia and industry in recent years. Some questions naturally arise that whether a TTS system can achieve human-level quality, how to define/judge that quality and how to achieve it. In this paper, we answer these questions by first defining the human-level quality based on the statistical significance of subjective measure and introducing appropriate guidelines to judge it, and then developing a TTS system called NaturalSpeech that achieves human-level quality on a benchmark dataset. Specifically, we leverage a variational autoencoder (VAE) for end-to-end text to waveform generation, with several key modules to enhance the capacity of the prior from text and reduce the complexity of the posterior from speech, including phoneme pre-training, differentiable duration modeling, bidirectional prior/posterior modeling, and a memory mechanism in VAE. Experiment evaluations on popular LJSpeech dataset show that our proposed NaturalSpeech achieves -0.01 CMOS (comparative mean opinion score) to human recordings at the sentence level, with Wilcoxon signed rank test at p-level p >> 0.05, which demonstrates no statistically significant difference from human recordings for the first time on this dataset.","url_abs":"https://arxiv.org/abs/2205.04421v2","url_pdf":"https://arxiv.org/pdf/2205.04421v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"naturalspeech-end-to-end-text-to-speech","repo_url":"https://github.com/microsoft/NeuralSpeech","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"naturalspeech-end-to-end-text-to-speech","repo_url":"https://github.com/daniilrobnikov/vits2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"naturalspeech-end-to-end-text-to-speech","repo_url":"https://github.com/heatz123/naturalspeech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-speech-synthesis-on-ljspeech","task":"Text-To-Speech Synthesis","dataset":"LJSpeech","model":"NaturalSpeech","rank_in_archive_order":1,"of":16,"metrics":{"Audio Quality MOS":"4.56"},"uses_additional_data":true},{"leaderboard":"/sota/text-to-speech-synthesis-on-ljspeech","task":"Text-To-Speech Synthesis","dataset":"LJSpeech","model":"VITS","rank_in_archive_order":2,"of":16,"metrics":{"Audio Quality MOS":"4.43"},"uses_additional_data":true},{"leaderboard":"/sota/text-to-speech-synthesis-on-ljspeech","task":"Text-To-Speech Synthesis","dataset":"LJSpeech","model":"FastSpeech 2 + HiFiGAN","rank_in_archive_order":5,"of":16,"metrics":{"Audio Quality MOS":"4.34"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2205.04421","atlas_url":"https://app.syntology.ai/?focus=2205.04421","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.04421"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/NeuralSpeech","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/daniilrobnikov/vits2","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/heatz123/naturalspeech","reach":{"status":"ok"}}],"summary":{"ran":3},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c55e3d6390482f28","entry":"discriminator_loss","repo":"daniilrobnikov/vits2","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/daniilrobnikov/vits2/blob/HEAD/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c55e3d6390482f28"}},{"code_sha256_prefix":"f9a2eedb621a3dda","entry":"feature_loss","repo":"daniilrobnikov/vits2","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/daniilrobnikov/vits2/blob/HEAD/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f9a2eedb621a3dda"}},{"code_sha256_prefix":"3eac5c1dd8f1b229","entry":"generator_loss","repo":"daniilrobnikov/vits2","repo_kind":"listed","path":"losses.py","file_url":"https://github.com/daniilrobnikov/vits2/blob/HEAD/losses.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3eac5c1dd8f1b229"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}