Bayesian Subspace HMM for the Zerospeech 2020 Challenge

05/19/2020
by   Bolaji Yusuf, et al.
0

In this paper we describe our submission to the Zerospeech 2020 challenge, where the participants are required to discover latent representations from unannotated speech, and to use those representations to perform speech synthesis, with synthesis quality used as a proxy metric for the unit quality. In our system, we use the Bayesian Subspace Hidden Markov Model (SHMM) for unit discovery. The SHMM models each unit as an HMM whose parameters are constrained to lie in a low dimensional subspace of the total parameter space which is trained to model phonetic variability. Our system compares favorably with the baseline on the human-evaluated character error rate while maintaining significantly lower unit bitrate.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2019

Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery

This work tackles the problem of learning a set of language specific aco...
research
11/04/2020

A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery

In this work, we propose a hierarchical subspace model for acoustic unit...
research
05/24/2020

Transformer VQ-VAE for Unsupervised Unit Discovery and Speech Synthesis: ZeroSpeech 2020 Challenge

In this paper, we report our submitted system for the ZeroSpeech 2020 ch...
research
04/16/2019

Unsupervised acoustic unit discovery for speech synthesis using discrete latent-variable neural networks

For our submission to the ZeroSpeech 2019 challenge, we apply discrete l...
research
10/24/2020

A Comparison of Discrete Latent Variable Models for Speech Representation Learning

Neural latent variable models enable the discovery of interesting struct...
research
10/31/2022

The Importance of Accurate Alignments in End-to-End Speech Synthesis

Unit selection synthesis systems required accurate segmentation and labe...
research
11/22/2020

Blade Envelopes Part I: Concept and Methodology

Blades manufactured through flank and point milling will likely exhibit ...

Please sign up or login with your details

Forgot password? Click here to reset