Hisashi Kawai

Quasi-Periodic Parallel WaveGAN Vocoder: A Non-Autoregressive Pitch-Dependent Dilated Convolution Model for Parametric Speech Generation

2020

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 …

Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-based ASR

2023 · arXiv (Cornell University)

Due to the modality discrepancy between textual and acoustic modeling, efficiently transferring linguistic knowledge from a pretrained language model (PLM) to acoustic encoding for automatic speech recognition (ASR) still remains a challenging task. In this …