{"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/accelerating-high-fidelity-waveform","title":"Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization","arxiv_id":"2408.08019","date":"2024-08-15","proceeding":null,"authors":["Sang-Hoon Lee","Ha-Yeong Choi","Seong-Whan Lee"],"abstract":"This paper introduces PeriodWave-Turbo, a high-fidelity and high-efficient waveform generation model via adversarial flow matching optimization. Recently, conditional flow matching (CFM) generative models have been successfully adopted for waveform generation tasks, leveraging a single vector field estimation objective for training. Although these models can generate high-fidelity waveform signals, they require significantly more ODE steps compared to GAN-based models, which only need a single generation step. Additionally, the generated samples often lack high-frequency information due to noisy vector field estimation, which fails to ensure high-frequency reproduction. To address this limitation, we enhance pre-trained CFM-based generative models by incorporating a fixed-step generator modification. We utilized reconstruction losses and adversarial feedback to accelerate high-fidelity waveform generation. Through adversarial flow matching optimization, it only requires 1,000 steps of fine-tuning to achieve state-of-the-art performance across various objective metrics. Moreover, we significantly reduce inference speed from 16 steps to 2 or 4 steps. Additionally, by scaling up the backbone of PeriodWave from 29M to 70M parameters for improved generalization, PeriodWave-Turbo achieves unprecedented performance, with a perceptual evaluation of speech quality (PESQ) score of 4.454 on the LibriTTS dataset. Audio samples, source code and checkpoints will be available at https://github.com/sh-lee-prml/PeriodWave.","url_abs":"https://arxiv.org/abs/2408.08019v1","url_pdf":"https://arxiv.org/pdf/2408.08019v1.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":"accelerating-high-fidelity-waveform","repo_url":"https://github.com/sh-lee-prml/periodwave","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-synthesis-on-libritts","task":"Speech Synthesis","dataset":"LibriTTS","model":"PeriodWave-Turbo-L","rank_in_archive_order":1,"of":15,"metrics":{"M-STFT":"0.7358","PESQ":"4.454","Periodicity":"0.0528","V/UV F1":"0.9756"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.08019","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}