{"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/rad-tts-parallel-flow-based-tts-with-robust","title":"RAD-TTS: Parallel Flow-Based TTS with Robust Alignment Learning and Diverse Synthesis","arxiv_id":null,"date":"2021-06-02","proceeding":"ICML Workshop INNF 2021 7","authors":["Kevin J. Shih","Rafael Valle","Rohan Badlani","Adrian Lancucki","Wei Ping","Bryan Catanzaro"],"abstract":"This work introduces a predominantly parallel, end-to-end TTS model based on normalizing flows.\n It extends prior parallel approaches by additionally modeling speech rhythm as a separate generative distribution to facilitate variable token duration during inference. We further propose a robust framework for the on-line extraction of speech-text alignments -- a critical yet highly unstable learning problem in end-to-end TTS frameworks. Our experiments demonstrate that our proposed techniques yield improved alignment quality, better output diversity compared to controlled baselines.","url_abs":"https://openreview.net/forum?id=0NQwnnwAORi","url_pdf":"https://openreview.net/pdf?id=0NQwnnwAORi","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":"rad-tts-parallel-flow-based-tts-with-robust","repo_url":"https://github.com/NVIDIA/radtts","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"rhythm","task_name":"Rhythm"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}