Automatic speech recognition is critical in natural human-centric interfaces for ambient intelligence. The performance of an automatic speech recognition system, however, degrades drastically when there is a mismatch between training and testing conditions. The aim of robust speech recognition is to overcome the mismatch problem so the result is a moderate and graceful degradation in recognitio...

Any algorithm for speech recognition always has a procedure for comparison of an input signal with the etalons available in memory, for definition of its belongings to an appropriate class. In this paper the definition of the set of etalons for the 1st version of the Automatic Speech Recognition (ASR) system for the Azerbaijani language is described.

The performance of current automatic speech recognition (ASR) systems is very sensitive to the presence of room reverberation in the incoming speech signal. We investigate a family of front-end speech representations that focus on slow changes in the the gross spectral structure of speech for their ability to improve the robustness of ASR systems to reverberation. A number of the front ends pro...

Although the topic ‘plasticity in speech perception’ is primarily concerned with the malleability of human speech perceptual behaviour, it may be illuminating to consider in parallel the degree to which current state-of-the-art ‘automatic speech recognition’ (ASR) systems also change their behaviour over time. This paper provides a review of the computational mechanisms underlying contemporary ...

This paper deals with new front-end feature improvements for Automatic Speech Recognition (ASR) robustness to changes in speech loudness. Our experiments show that applying a RASTA– like filter gives a significant improvement in robustness to speech loudness change, leading to an up to 4% PER reduction.