Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends

TL;DR

This paper provides a comprehensive survey of deep representation learning techniques in speech processing, highlighting recent advances, challenges, and future trends across ASR, speaker recognition, and emotion recognition.

Contribution

It uniquely consolidates scattered research on speech representation learning, covering three key areas and emphasizing deep learning's role in automatic feature extraction.

Findings

Representation learning improves speech task performance

Deep learning reduces dependence on manual feature engineering

Survey covers recent advances and future directions

Abstract

Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to make prediction and classification decisions. There are two main drawbacks to this approach: firstly, the feature engineering being manual is cumbersome and requires human knowledge; and secondly, the designed features might not be best for the objective at hand. This has motivated the adoption of a recent trend in speech community towards utilisation of representation learning techniques, which can learn an intermediate representation of the input signal automatically that better suits the task at hand and hence lead to improved performance. The significance of representation learning has increased with advances in deep learning (DL), where the representations are more useful and less dependent on human knowledge, making it very conducive for tasks like classification, prediction, etc. The main contribution of this paper is to present an up-to-date and comprehensive survey on different techniques of speech representation learning by bringing together the scattered research across three distinct research areas including Automatic Speech Recognition (ASR), Speaker Recognition (SR), and Speaker Emotion Recognition (SER). Recent reviews in speech have been conducted for ASR, SR, and SER, however, none of these has focused on the representation learning from speech -- a gap that our survey aims to bridge.