A Fully Time-domain Neural Model for Subband-based Speech Synthesizer

Abstract

This paper introduces a deep neural network model for subband-based speech synthesizer. The model benefits from the short bandwidth of the subband signals to reduce the complexity of the time-domain speech generator. We employed the multi-level wavelet analysis/synthesis to decompose/reconstruct the signal into subbands in time domain. Inspired from the WaveNet, a convolutional neural network (CNN) model predicts subband speech signals fully in time domain. Due to the short bandwidth of the subbands, a simple network architecture is enough to train the simple patterns of the subbands accurately. In the ground truth experiments with teacher-forcing, the subband synthesizer outperforms the fullband model significantly in terms of both subjective and objective measures. In addition, by conditioning the model on the phoneme sequence using a pronunciation dictionary, we have achieved the fully time-domain neural model for subband-based text-to-speech (TTS) synthesizer, which is nearly end-to-end. The generated speech of the subband TTS shows comparable quality as the fullband one with a slighter network architecture for each subband.

5 pages, 3 figure

References in corpus (6)

• WaveNet: A Generative Model for Raw Audio
• Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
• Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention
• Emotional End-to-End Neural Speech Synthesizer
• Fast Wavenet Generation Algorithm
• Stochastic WaveNet: A Generative Latent Variable Model for Sequential Data