Learn More
We address the theoretical and practical issues involved in ASR when some of the observation data for the target signal is masked by other signals. Techniques discussed range from simple missing data imputation to Bayesian optimal classification. We have developed the Bayesian approach because this allows prior knowledge to be incorporated naturally into(More)
1. Introduction Possible application of the missing data techniques to the problem of robust speech recognition was my area of interest in the last six months. In the following sections, some of the problems of robustness in speech recognition, proposed techniques for dealing with and missing data approach will be described. Ways for extension of missing(More)
In this paper, we develop di€erent mathematical models in the framework of the multi-stream paradigm for noise robust automatic speech recognition (ASR), and discuss their close relationship with human speech perception. Largely inspired by Fletcher's ``product-of-errors'' rule (PoE rule) in psychoacoustics, multi-band ASR aims for robustness to data(More)
In this report, we investigate and compare diierent subband-based Automatic Speech Recognition (ASR) approaches, including an original approach, referred to as the \full combination approach", based on an estimate of the (noise-) weighted sum of posterior probabilities for all possible subband combinations. We show that the proposed estimate is a good(More)
Feature projection by non-linear discriminant analysis (NLDA) can substantially increase classification performance. In automatic speech recognition (ASR) the projection provided by the pre-squashed outputs from a one hidden layer multi-layer perceptron (MLP) trained to recognise speech sub-units (phonemes) has previously been shown to significantly(More)
In the " missing data " (MD) approach to noise robust automatic speech recognition (ASR), speech models are trained on clean data, and during recognition sections of spectral data dominated by noise are detected and treated as " missing ". However, this all-or-nothing hard decision about which data is missing does not accurately reflect the probabilistic(More)
The performance of most ASR systems degrades rapidly with data mismatch relative to the data used in training. Under many realistic noise conditions a significant proportion of the spectral representation of a speech signal, which is highly redundant, remains uncorrupted. In the " missing feature " approach to this problem mismatching data is simply(More)