An accurate objective prediction of human speech intelligibility is of interest for many
applications such as the evaluation of signal processing algorithms. To predict the speech …

This paper proposes multistream CNN, a novel neural network architecture for robust
acoustic modeling in speech recognition tasks. The proposed architecture processes input …

This paper makes several contributions to automatic lyrics transcription (ALT) research. Our
main contribution is a novel variant of the Multistreaming Time-Delay Neural Network …

This paper postulates that linguistic message in speech is coded redundantly in both the
time and the frequency domains. Such redundant coding of the message in the signal …

We propose an environment adaptation approach that improves deep speech enhancement
models via minimizing the Kullback-Leibler divergence between posterior probabilities …

Robustness of automatic speech recognition (ASR) to acoustic mismatches can be improved
by multistream framework. Frequently used approach to combine decisions from individual …

New efficient measures for estimating uncertainty of deep neural network (DNN) classifiers
are proposed and successfully applied to multistream-based unsupervised adaptation of …

In this paper, we propose a novel method to capture energy modulations from different
frequency bands in speech into frame-level feature vectors, called Modulation-vectors or M …

Exploiting multiple microphones has been a widely-used strategy for robust automatic
speech recognition (ASR). Particularly, in a general hands-free scenario, acquisition of …

Quality evaluation of digitally-transmitted speech is an important prerequisite to ensure the
required quality of telecommunication service. Although formal subjective listening tests still …