LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation
Abstract
Recently, the application of diffusion models has facilitated the significant development of speech and audio generation. Nevertheless, the quality of samples generated by diffusion models still needs improvement. And the effectiveness of the method is accompanied by the extensive number of sampling steps, leading to an extended synthesis time necessary for generating high-quality audio. Previous Text-to-Audio (TTA) methods mostly used diffusion models in the latent space for audio generation. In this paper, we explore the integration of the Flow Matching (FM) model into the audio latent space for audio generation. The FM is an alternative simulation-free method that trains continuous normalization flows (CNF) based on regressing vector fields. We demonstrate that our model significantly enhances the quality of generated audio samples, achieving better performance than prior models. Moreover, it reduces the number of inference steps to ten steps almost without sacrificing performance.
Keywords
Cite
@article{arxiv.2406.08203,
title = {LAFMA: A Latent Flow Matching Model for Text-to-Audio Generation},
author = {Wenhao Guan and Kaidi Wang and Wangjin Zhou and Yang Wang and Feng Deng and Hui Wang and Lin Li and Qingyang Hong and Yong Qin},
journal= {arXiv preprint arXiv:2406.08203},
year = {2024}
}
Comments
Accepted at Interspeech2024