Exploring TTS without T Using Biologically/Psychologically Motivated Neural Network Modules (ZeroSpeech 2020)

Abstract

In this study, we reported our exploration of Text-To-Speech without Text (TTS without T) in the Zero Resource Speech Challenge 2020, in which participants proposed an end-to-end, unsupervised system that learned speech recognition and TTS together. We addressed the challenge using biologically/psychologically motivated modules of Artificial Neural Networks (ANN), with a particular interest in unsupervised learning of human language as a biological/psychological problem. The system first processes Mel Frequency Cepstral Coefficient (MFCC) frames with an Echo-State Network (ESN), and simulates computations in cortical microcircuits. The outcome is discretized by our original Variational Autoencoder (VAE) that implements the Dirichlet-based Bayesian clustering widely accepted in computational linguistics and cognitive science. The discretized signal is then reverted into sound waveform via a neural-network implementation of the source-filter model for speech production.

arXiv commentAccepted in INTERSPEECH 2020

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Neural Machine Translation by Jointly Learning to Align and Translate
• Categorical Reparameterization with Gumbel-Softmax
• Neural Discrete Representation Learning
• A segmental framework for fully-unsupervised large-vocabulary speech recognition
• VQVAE Unsupervised Unit Discovery and Multi-scale Code2Spec Inverter for Zerospeech Challenge 2019

Cited by in corpus (3)

• Self-supervised language learning from raw audio: Lessons from the Zero Resource Speech Challenge
• The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units
• Towards Induction of Structured Phoneme Inventories