ECAPA-TDNN for Multi-speaker Text-to-speech Synthesis
This work addresses the challenge of accurate speaker modeling in multi-speaker TTS, which is incremental as it adapts existing components from speaker verification and TTS tasks.
The paper tackled the problem of insufficient speaker information capture in multi-speaker TTS by proposing an end-to-end method using an ECAPA-TDNN speaker encoder, achieving better naturalness and similarity for both seen and unseen speakers.
In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress. However, the current speaker encoder models used in these methods still cannot capture enough speaker information. In this paper, we focus on accurate speaker encoder modeling and propose an end-to-end method that can generate high-quality speech and better similarity for both seen and unseen speakers. The proposed architecture consists of three separately trained components: a speaker encoder based on the state-of-the-art ECAPA-TDNN model which is derived from speaker verification task, a FastSpeech2 based synthesizer, and a HiFi-GAN vocoder. The comparison among different speaker encoder models shows our proposed method can achieve better naturalness and similarity. To efficiently evaluate our synthesized speech, we are the first to adopt deep learning based automatic MOS evaluation methods to assess our results, and these methods show great potential in automatic speech quality assessment.