Quasi-periodic Parallel Wavegan Vocoder: A Non-autoregressive Pitch-dependent Dilated Convolution Model For Parametric Speech Generation

Abstract

In this paper, we propose a parallel WaveGAN (PWG)-like neural vocoder with a quasi-periodic (QP) architecture to improve the pitch controllability of PWG. PWG is a compact non-autoregressive (non-AR) speech generation model, whose generative speed is much faster than real time. While utilizing PWG as a vocoder to generate speech on the basis of acoustic features such as spectral and prosodic features, PWG generates high-fidelity speech. However, when the input acoustic features include unseen pitches, the pitch accuracy of PWG-generated speech degrades because of the fixed and generic network of PWG without prior knowledge of speech periodicity. The proposed QPPWG adopts a pitch-dependent dilated convolution network (PDCNN) module, which introduces the pitch information into PWG via the dynamically changed network architecture, to improve the pitch controllability and speech modeling capability of vanilla PWG. Both objective and subjective evaluation results show the higher pitch accu

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keywu2020quasi

Related papers

• Quasi-periodic Wavenet Vocoder: A Pitch Dependent Dilated Convolution Model For Parametric Speech Generation (2019)7.50
• Periodgrad: Towards Pitch-controllable Neural Vocoder Based On A Diffusion Probabilistic Model (2024)0.00
• Statistical Voice Conversion With Quasi-periodic Wavenet Vocoder (2019)3.58
• Puffin: Pitch-synchronous Neural Waveform Generation For Fullband Speech On Modest Devices (2022)3.58
• Parallel Wavegan: A Fast Waveform Generation Model Based On Generative Adversarial Networks With Multi-resolution Spectrogram (2019)0.00
• Parallel Waveform Synthesis Based On Generative Adversarial Networks With Voicing-aware Conditional Discriminators (2020)7.16
• Probability Density Distillation With Generative Adversarial Networks For High-quality Parallel Waveform Generation (2019)10.48
• Unified Source-filter GAN: Unified Source-filter Network Based On Factorization Of Quasi-periodic Parallel Wavegan (2021)7.81