Generative Speech Coding with Predictive Variance Regularization

The recent emergence of machine-learning based generative models for speech suggests a significant reduction in bit rate for speech codecs is possible. However, the performance of generative models deteriorates significantly with the distortions present in real-world input signals. We argue that thi...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-02
Main Authors: Kleijn, W Bastiaan, Storus, Andrew, Chinen, Michael, Denton, Tom, Lim, Felicia S C, Luebs, Alejandro, Skoglund, Jan, Yeh, Hengchin
Format: Article
Language:English
Subjects:
Autoregressive models
Codec
Coding
Machine learning
Noise reduction
Performance evaluation
Regularization
Sensitivity
Speech
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The recent emergence of machine-learning based generative models for speech suggests a significant reduction in bit rate for speech codecs is possible. However, the performance of generative models deteriorates significantly with the distortions present in real-world input signals. We argue that this deterioration is due to the sensitivity of the maximum likelihood criterion to outliers and the ineffectiveness of modeling a sum of independent signals with a single autoregressive model. We introduce predictive-variance regularization to reduce the sensitivity to outliers, resulting in a significant increase in performance. We show that noise reduction to remove unwanted signals can significantly increase performance. We provide extensive subjective performance evaluations that show that our system based on generative modeling provides state-of-the-art coding performance at 3 kb/s for real-world speech signals at reasonable computational complexity.
ISSN:2331-8422