{"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/fastdiff-a-fast-conditional-diffusion-model","title":"FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis","arxiv_id":"2204.09934","date":"2022-04-21","proceeding":null,"authors":["Rongjie Huang","Max W. Y. Lam","Jun Wang","Dan Su","Dong Yu","Yi Ren","Zhou Zhao"],"abstract":"Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. FastDiff employs a stack of time-aware location-variable convolutions of diverse receptive field patterns to efficiently model long-term time dependencies with adaptive conditions. A noise schedule predictor is also adopted to reduce the sampling steps without sacrificing the generation quality. Based on FastDiff, we design an end-to-end text-to-speech synthesizer, FastDiff-TTS, which generates high-fidelity speech waveforms without any intermediate feature (e.g., Mel-spectrogram). Our evaluation of FastDiff demonstrates the state-of-the-art results with higher-quality (MOS 4.28) speech samples. Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time. We further show that FastDiff generalized well to the mel-spectrogram inversion of unseen speakers, and FastDiff-TTS outperformed other competing methods in end-to-end text-to-speech synthesis. Audio samples are available at \\url{https://FastDiff.github.io/}.","url_abs":"https://arxiv.org/abs/2204.09934v1","url_pdf":"https://arxiv.org/pdf/2204.09934v1.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":"fastdiff-a-fast-conditional-diffusion-model","repo_url":"https://github.com/Rongjiehuang/FastDiff","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fastdiff-a-fast-conditional-diffusion-model","repo_url":"https://github.com/Rongjiehuang/ProDiff","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":null,"task_name":"GPU"},{"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":"high","task_name":"Vocal Bursts Intensity Prediction"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-speech-synthesis-on-ljspeech","task":"Text-To-Speech Synthesis","dataset":"LJSpeech","model":"FastDiff (4 steps)","rank_in_archive_order":7,"of":16,"metrics":{"Audio Quality MOS":"4.28"},"uses_additional_data":true},{"leaderboard":"/sota/text-to-speech-synthesis-on-ljspeech","task":"Text-To-Speech Synthesis","dataset":"LJSpeech","model":"FastDiff-TTS","rank_in_archive_order":8,"of":16,"metrics":{"Audio Quality MOS":"4.03"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.09934","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.09934"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/Rongjiehuang/ProDiff","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Rongjiehuang/FastDiff","reach":null}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":4,"samples":[{"code_sha256_prefix":"063a10faddb0c71c","entry":"DiffusionDBlock","repo":"Rongjiehuang/FastDiff","repo_kind":"official","path":"modules/FastDiff/module/FastDiff_model.py","file_url":"https://github.com/Rongjiehuang/FastDiff/blob/HEAD/modules/FastDiff/module/FastDiff_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"063a10faddb0c71c"}},{"code_sha256_prefix":"618fdcca37cd6ab6","entry":"FastDiff","repo":"Rongjiehuang/FastDiff","repo_kind":"official","path":"modules/FastDiff/module/FastDiff_model.py","file_url":"https://github.com/Rongjiehuang/FastDiff/blob/HEAD/modules/FastDiff/module/FastDiff_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"618fdcca37cd6ab6"}},{"code_sha256_prefix":"0e0ec28ceb2b7311","entry":"KernelPredictor","repo":"Rongjiehuang/FastDiff","repo_kind":"official","path":"modules/FastDiff/module/FastDiff_model.py","file_url":"https://github.com/Rongjiehuang/FastDiff/blob/HEAD/modules/FastDiff/module/FastDiff_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0e0ec28ceb2b7311"}},{"code_sha256_prefix":"55b06076c5a883c9","entry":"TimeAware_LVCBlock","repo":"Rongjiehuang/FastDiff","repo_kind":"official","path":"modules/FastDiff/module/FastDiff_model.py","file_url":"https://github.com/Rongjiehuang/FastDiff/blob/HEAD/modules/FastDiff/module/FastDiff_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"55b06076c5a883c9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}