Paper · arXiv 2309.03199
Matcha-TTS: A fast TTS architecture with conditional flow matching
Shivam Mehta, Ruibo Tu, Jonas Beskow, Éva Székely, Gustav Eje Henter
Matcha-TTS is a new encoder-decoder architecture for text-to-speech that uses optimal-transport conditional flow matching to produce high-quality outputs quickly and efficiently, outperforming existing models in speed, memory usage, and audio quality.
Abstract
We introduce Matcha-TTS, a new encoder-decoder architecture for speedy TTS acoustic modelling, trained using optimal-transport conditional flow matching (OT-CFM). This yields an ODE-based decoder capable of high output quality in fewer synthesis steps than models trained using score matching. Careful design choices additionally ensure each synthesis step is fast to run. The method is probabilistic, non-autoregressive, and learns to speak from scratch without external alignments. Compared to strong pre-trained baseline models, the Matcha-TTS system has the smallest memory footprint, rivals the speed of the fastest models on long utterances, and attains the highest mean opinion score in a listening test. Please see https://shivammehta25.github.io/Matcha-TTS/ for audio examples, code, and pre-trained models.