Biologically inspired methods for automatic speech understanding

Abstract

Automatic Speech Recognition (ASR) and Understanding (ASU) systems heavily rely on machine learning techniques to solve the problem of mapping spoken utterances into words and meanings. The statistical methods employed, however, greatly deviate from the processes involved in human language acquisition in a number of key aspects. Although ASR and ASU have recently reached a level of accuracy that is sufficient for some practical applications, there are still severe limitations due, for example, to the amount of training data required and the lack of generalization of the resulting models. In our opinion, there is a need for a paradigm shift and speech technology should address some of the challenges that humans face when learning a first language and that are currently ignored by the ASR and ASU methods. In this paper, we point out some of the aspects that could lead to more robust and flexible models, and we describe some of the research we and other researchers have performed in the area. © 2013 Springer-Verlag.