Lightweight Zero-shot Text-to-Speech with Mixture of Adapters

TL;DR

This paper introduces a lightweight zero-shot text-to-speech method using a mixture of adapters, enabling high-quality speaker adaptation with fewer parameters and faster inference.

Contribution

The paper proposes integrating a mixture of adapters into a non-autoregressive TTS model for efficient zero-shot speaker adaptation.

Findings

Achieves better speech quality than baseline

Uses less than 40% of parameters of large models

Provides 1.9x faster inference speed

Abstract

The advancements in zero-shot text-to-speech (TTS) methods, based on large-scale models, have demonstrated high fidelity in reproducing speaker characteristics. However, these models are too large for practical daily use. We propose a lightweight zero-shot TTS method using a mixture of adapters (MoA). Our proposed method incorporates MoA modules into the decoder and the variance adapter of a non-autoregressive TTS model. These modules enhance the ability to adapt a wide variety of speakers in a zero-shot manner by selecting appropriate adapters associated with speaker characteristics on the basis of speaker embeddings. Our method achieves high-quality speech synthesis with minimal additional parameters. Through objective and subjective evaluations, we confirmed that our method achieves better performance than the baseline with less than 40\% of parameters at 1.9 times faster inference speed. Audio samples are available on our demo page (https://ntt-hilab-gensp.github.io/is2024lightweightTTS/).