WaveNeXt: ConvNeXt-Based Fast Neural Vocoder Without ISTFT layer
Takuma Okamoto, Haruki Yamashita, Yamato Ohtani, Tomoki Toda, Hisashi Kawai · 2023
A recently proposed neural vocoder, Vocos, can perform inference ten times faster than HiFi-GAN because of its use of ConvNeXt layers that can predict high-resolution short-time Fourier transform (STFT) spectra and an inverse STFT layer. To improve synthesis quality while preserving inference speed, this paper proposes an alternative ConvNeXt-based fast neural vocoder, WaveNeXt, in which the inverse STFT layer in Vocos is replaced with a trainable linear layer that can directly predict speech waveform samples without STFT spectra. Additionally, by integrating the JETS-based end-to-end text-to-speech (E2E TTS) framework, E2E TTS models can also be constructed with Vocos and WaveNeXt. Furthermore, full-band models with a sampling frequency of 48 kHz were investigated. The results of experiments for both the analysis-synthesis and E2E TTS conditions demonstrate that the proposed WaveNeXt can achieve higher quality synthesis than Vocos while preserving its inference speed.