NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers

TL;DR

NanoVoice is a fast and parameter-efficient personalized text-to-speech model that adapts to multiple speakers simultaneously, reducing training time and resource usage while maintaining high quality.

Contribution

It introduces a batch-wise speaker adaptation method with parameter sharing and a trainable scale matrix, enabling efficient multi-speaker TTS training.

Findings

Training time reduced by 4x

Parameter usage decreased by 45%

Performance comparable to baseline models

Abstract

We present NanoVoice, a personalized text-to-speech model that efficiently constructs voice adapters for multiple speakers simultaneously. NanoVoice introduces a batch-wise speaker adaptation technique capable of fine-tuning multiple references in parallel, significantly reducing training time. Beyond building separate adapters for each speaker, we also propose a parameter sharing technique that reduces the number of parameters used for speaker adaptation. By incorporating a novel trainable scale matrix, NanoVoice mitigates potential performance degradation during parameter sharing. NanoVoice achieves performance comparable to the baselines, while training 4 times faster and using 45 percent fewer parameters for speaker adaptation with 40 reference voices. Extensive ablation studies and analysis further validate the efficiency of our model.