May 20, 2013

Machine Learning Paradigms for Speech Recognition: An Overview

IEEE/ACM Transactions on Audio, Speech, and Language Processing

By: Li Deng, Xiao Li

Abstract

Automatic Speech Recognition (ASR) has historically been a driving force behind many machine learning (ML) techniques, including the ubiquitously used hidden Markov model, discriminative learning, Bayesian learning, and adaptive learning. Moreover, ML can and occasionally does use ASR as a large-scale, realistic application to rigorously test the effectiveness of a given technique, and to inspire new problems arising from the inherently sequential nature of speech. On the other hand, even though ASR is available commercially for some applications, it is largely an unsolved problem — for many applications, the performance of ASR is not on par with human performance. New insight from modern ML methodology shows great promise to advance the state-of-the-art in ASR technology.

This article provides readers with an overview of modern ML techniques as utilized in current and as relevant to future ASR research and systems.The intent of the article is to foster further cross-pollination between the ML and ASR communities than what has occurred in the past. The article is organized according to the major ML paradigms that are either popular already or have potential for making significant contributions to ASR technology.

The paradigms presented and elaborated in this overview include generative and discriminative learning; supervised, unsupervised, semi-supervised, and active learning; adaptive and multi-task learning; and Bayesian learning. These learning paradigms are motivated and discussed in the context of ASR technology and applications. We finally present and analyze recent developments of deep learning and learning with sparse representations, focusing on their direct relevance to advancing ASR technology.