Continuous Wavelet Vocoder-based Decomposition of Parametric Speech Waveform Synthesis

2021/06/12 by Al-Radhi, Mohammed Salah, Csapó, Tamás Gábor, Zainkó, Csaba +1
#Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2106.06863

Abstract

To date, various speech technology systems have adopted the vocoder approach, a method for synthesizing speech waveform that shows a major role in the performance of statistical parametric speech synthesis. WaveNet one of the best models that nearly resembles the human voice, has to generate a waveform in a time consuming sequential manner with an extremely complex structure of its neural networks.

Related

• Towards Parametric Speech Synthesis Using Gaussian-Markov Model of Spectral Envelope and Wavelet-Based Decomposition of F0
• LP-WaveNet: Linear Prediction-based WaveNet Speech Synthesis
• ExcitNet vocoder: A neural excitation model for parametric speech synthesis systems
• WaveCycleGAN: Synthetic-to-natural speech waveform conversion using cycle-consistent adversarial networks
• WaveNODE: A Continuous Normalizing Flow for Speech Synthesis