Metis: A Foundation Speech Generation Model with Masked Generative Pre-training

TL;DR

Metis is a versatile foundation speech generation model that uses masked generative pre-training on large-scale unlabeled speech data, enabling efficient adaptation to diverse tasks with minimal data and parameters.

Contribution

It introduces a unified pre-training and fine-tuning framework utilizing discrete speech representations, achieving state-of-the-art results across multiple speech generation tasks.

Findings

Outperforms task-specific models on five speech tasks.

Operates effectively with fewer than 20M trainable parameters.

Requires 300 times less training data than previous methods.

Abstract

We introduce Metis, a foundation model for unified speech generation. Unlike previous task-specific or multi-task models, Metis follows a pre-training and fine-tuning paradigm. It is pre-trained on large-scale unlabeled speech data using masked generative modeling and then fine-tuned to adapt to diverse speech generation tasks. Specifically, 1) Metis utilizes two discrete speech representations: SSL tokens derived from speech self-supervised learning (SSL) features, and acoustic tokens directly quantized from waveforms. 2) Metis performs masked generative pre-training on SSL tokens, utilizing 300K hours of diverse speech data, without any additional condition. 3) Through fine-tuning with task-specific conditions, Metis achieves efficient adaptation to various speech generation tasks while supporting multimodal input, even when using limited data and trainable parameters. Experiments demonstrate that Metis can serve as a foundation model for unified speech generation: Metis outperforms state-of-the-art task-specific or multi-task systems across five speech generation tasks, including zero-shot text-to-speech, voice conversion, target speaker extraction, speech enhancement, and lip-to-speech, even with fewer than 20M trainable parameters or 300 times less training data. Audio samples are are available at https://metis-demo.github.io/.