Towards Parametric Speech Synthesis Using Gaussian-Markov Model of Spectral Envelope and Wavelet-Based Decomposition of F0

08/15/2022
by   Mohammed Salah Al-Radhi, et al.
0

Neural network-based Text-to-Speech has significantly improved the quality of synthesized speech. Prominent methods (e.g., Tacotron2, FastSpeech, FastPitch) usually generate Mel-spectrogram from text and then synthesize speech using vocoder (e.g., WaveNet, WaveGlow, HiFiGAN). Compared with traditional parametric approaches (e.g., STRAIGHT and WORLD), neural vocoder based end-to-end models suffer from slow inference speed, and the synthesized speech is usually not robust and lack of controllability. In this work, we propose a novel updated vocoder, which is a simple signal model to train and easy to generate waveforms. We use the Gaussian-Markov model toward robust learning of spectral envelope and wavelet-based statistical signal processing to characterize and decompose F0 features. It can retain the fine spectral envelope and achieve high controllability of natural speech. The experimental results demonstrate that our proposed vocoder achieves better naturalness of reconstructed speech than the conventional STRAIGHT vocoder, slightly better than WaveNet, and somewhat worse than the WaveRNN.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/22/2019

FastSpeech: Fast, Robust and Controllable Text to Speech

Neural network based end-to-end text to speech (TTS) has significantly i...
research
11/09/2018

ExcitNet vocoder: A neural excitation model for parametric speech synthesis systems

This paper proposes a WaveNet-based neural excitation model (ExcitNet) f...
research
04/10/2019

RawNet: Fast End-to-End Neural Vocoder

Neural networks based vocoders have recently demonstrated the powerful a...
research
01/22/2016

Speech vocoding for laboratory phonology

Using phonological speech vocoding, we propose a platform for exploring ...
research
08/18/2016

DNN-based Speech Synthesis for Indian Languages from ASCII text

Text-to-Speech synthesis in Indian languages has a seen lot of progress ...
research
11/11/2020

WaDeNet: Wavelet Decomposition based CNN for Speech Processing

Existing speech processing systems consist of different modules, individ...
research
01/02/2020

Eigenresiduals for improved Parametric Speech Synthesis

Statistical parametric speech synthesizers have recently shown their abi...

Please sign up or login with your details

Forgot password? Click here to reset