Wave-u-net Discriminator: Fast And Lightweight Discriminator For Generative Adversarial Network-based Speech Synthesis

Abstract

In speech synthesis, a generative adversarial network (GAN), training a generator (speech synthesizer) and a discriminator in a min-max game, is widely used to improve speech quality. An ensemble of discriminators is commonly used in recent neural vocoders (e.g., HiFi-GAN) and end-to-end text-to-speech (TTS) systems (e.g., VITS) to scrutinize waveforms from multiple perspectives. Such discriminators allow synthesized speech to adequately approach real speech; however, they require an increase in the model size and computation time according to the increase in the number of discriminators. Alternatively, this study proposes a Wave-U-Net discriminator, which is a single but expressive discriminator with Wave-U-Net architecture. This discriminator is unique; it can assess a waveform in a sample-wise manner with the same resolution as the input signal, while extracting multilevel features via an encoder and decoder with skip connections. This architecture provides a generator with sufficie

Stats

• citations6
• S2 citations—
• github stars0
• HF likes0
• heat score6.34
• arxiv keykaneko2023wave

Related papers

• Vnet: A Gan-based Multi-tier Discriminator Network For Speech Synthesis Vocoders (2024)2.26
• Parallel Waveform Synthesis Based On Generative Adversarial Networks With Voicing-aware Conditional Discriminators (2020)7.16
• Parallel Wavegan: A Fast Waveform Generation Model Based On Generative Adversarial Networks With Multi-resolution Spectrogram (2019)0.00
• Waveform Generation For Text-to-speech Synthesis Using Pitch-synchronous Multi-scale Generative Adversarial Networks (2018)8.35
• Wavefit: An Iterative And Non-autoregressive Neural Vocoder Based On Fixed-point Iteration (2022)9.41
• High Fidelity Speech Synthesis With Adversarial Networks (2019)0.00
• Generative Adversarial Network Based Speaker Adaptation For High Fidelity Wavenet Vocoder (2018)5.84
• Hifi-wavegan: Generative Adversarial Network With Auxiliary Spectrogram-phase Loss For High-fidelity Singing Voice Generation (2022)0.00