Speech processing for under-resourced languages is an active field of research, which has experienced significant progress during the past decade. We propose, in this paper, a survey that focuses on automatic speech recognition (ASR) for these languages. The definition of under-resourced languages and the challenges associated to them are first defined. The main part of the paper is a literature review of the recent (last 8 years) contributions made in ASR for under-resourced languages. Examples of past projects and future trends when dealing with under-resourced languages are also presented. We believe that this paper will be a good starting point for anyone interested to initiate research in (or operational development of) ASR for one or several under-resourced languages. It should be clear, however, that many of the issues and approaches presented here, apply to speech technology in general (text-to-speech synthesis for instance).

No abstract

No abstract

The differences in classification and training performance of three- and four-layer (one- and two-hidden-layer) fully interconnected feedforward neural nets are investigated. To obtain results which do not merely reflect performance on a particular data set, the networks are trained on various distributions, which are themselves drawn from a distribution of distributions. Experimental results indicate that four-layered networks are more prone to fall into bad local minima, but that three- and four-layered networks perform similarly in all other respects.

Various techniques of optimizing criterion functions to train neural-net classifiers are investigated. These techniques include three standard deterministic techniques (variable metric, conjugate gradient, and steepest descent), and a new stochastic technique. It is found that the stochastic technique is preferable on problems with large training sets and that the convergence rates of the variable metric and conjugate gradient techniques are similar.

The training of neural net classifiers is often hampered by the occurrence of local minima, which results in the attainment of inferior classification performance. It has been shown that the occurrence of local minima in the criterion function is often related to specific patterns of defects in the classifier. In particular, three main causes for local minima were identified. Such an understanding of the physical correlates of local minima suggests sensible ways of choosing the weights from which the training process is initiated. A method of initialization is introduced and shown to decrease the possibility of local minima occurring on various test problems.

No abstract

No abstract