Performance of speech recognition systems strongly degrades in the presence of background noise, like the driving noise inside a car. In contrast to existing works, we aim to improve noise robustness focusing on all major levels of speech recognition: feature extraction, feature enhancement, speech modelling, and training. Thereby, we give an overview of promising auditory modelling concepts, s...

Speech perception deficits in developmental dyslexia were investigated in quiet and various noise conditions. Dyslexics exhibited clear speech perception deficits in noise but not in silence. Place-of-articulation was more affected than voicing or manner-of-articulation. Speech-perception-in-noise deficits persisted when performance of dyslexics was compared to that of much younger children mat...

Although cochlear implant (CI) users have enjoyed good speech recognition in quiet, they still have difficulties understanding speech in noise. We conducted three experiments to determine whether a directional microphone and an adaptive multichannel noise reduction algorithm could enhance CI performance in noise and whether Speech Transmission Index (STI) can be used to predict CI performance i...

Three experiments compared the intelligibilities of helium-speech and normal speech when both were masked by loud noise. Recordings were made of five talkers reading intelligibility word-lists. Several panels of listeners heard these recordings masked by different levels of background noise. In Experiment I, a fatigue effect seemed at first to be present differentially for the helium-speech, su...

In this paper, we propose a new blind spatial subtraction array (BSSA) which contains an accurate noise estimator based on independent component analysis (ICA) to realize a noise-robust hands-free speech recognition. First, a preliminary experiment suggests that the conventional ICA is proficient in the noise estimation rather than the direct speech estimation in real environments, where the ta...

Speech understanding in noise is affected by both the energetic and informational masking components of the background noise. In addition, when the background noise is everyday speech, the relative contributions of the energetic and informational masking components to the overall difficulties in understanding speech are unclear. This study estimated informational masking effects, in conversatio...

Speech separation can be treated as a mask estimation problem where interference-dominant portions are masked in a timefrequency representation of noisy speech. In supervised speech separation, a classifier is typically trained on a mixture set of speech and noise. Improving the generalization of a classifier is challenging, especially when interfering noise is strong and nonstationary. Expansi...

In this paper, we present a speech enhancement technique that uses a-priori information about both speech and noise. The apriori information consists of speech and noise spectral shapes stored in trained codebooks. The excitation variances of speech and noise are determined through the optimization of a criterion that finds the best fit between the noisy observation and the model represented by...

Speech separation can be treated as a mask estimation problem, where interference-dominant portions are masked in a time-frequency representation of noisy speech. In supervised speech separation, a classifier is typically trained on a mixture set of speech and noise. It is important to efficiently utilize limited training data to make the classifier generalize well. When target speech is severe...