MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model
Abstract
Codec-based text-to-speech (TTS) models have shown impressive quality with zero-shot voice cloning abilities. However, they often struggle with more expressive references or complex text inputs. We present MARS6, a robust encoder-decoder transformer for rapid, expressive TTS. MARS6 is built on recent improvements in spoken language modelling. Utilizing a hierarchical setup for its decoder, new speech tokens are processed at a rate of only 12 Hz, enabling efficient modelling of long-form text while retaining reconstruction quality. We combine several recent training and inference techniques to reduce repetitive generation and improve output stability and quality. This enables the 70M-parameter MARS6 to achieve similar performance to models many times larger. We show this in objective and subjective evaluations, comparing TTS output quality and reference speaker cloning ability. Project page: https://camb-ai.github.io/mars6-turbo/
Cite
@article{arxiv.2501.05787,
title = {MARS6: A Small and Robust Hierarchical-Codec Text-to-Speech Model},
author = {Matthew Baas and Pieter Scholtz and Arnav Mehta and Elliott Dyson and Akshat Prakash and Herman Kamper},
journal= {arXiv preprint arXiv:2501.05787},
year = {2025}
}
Comments
5 pages, 2 figures, 1 table. Accepted at ICASSP 2025