Recently, Mixture of Experts (MoE) based Transformer has shown promising results in many
domains. This is largely due to the following advantages of this architecture: firstly, MoE …

Distant speech recognition is a highly challenging task due to background noise,
reverberation, and speech overlap. Recently, there has been an increasing focus on …

Speech recognizers trained on close-talking speech do not generalize to distant speech and
the word error rate degradation can be as large as 40% absolute. Most studies focus on …

Far-field speech recognition is an important yet challenging task due to low signal to noise
ratio. In this paper, three novel deep neural network architectures are explored to improve …

Integration of multiple microphone data is one of the key ways to achieve robust speech
recognition in noisy environments or when the speaker is located at some distance from the …

Self-attention networks (SAN) have been introduced into automatic speech recognition
(ASR) and achieved state-of-the-art performance owing to its superior ability in capturing …

Although great progress has been made in automatic speech recognition (ASR), significant
performance degradation still exists in noisy environments. In this paper, a novel factor …

Abstract Automatic Speech Recognition (ASR) has recently proved to be a useful tool to
reduce the workload of air traffic controllers leading to significant gains in operational …

Although great progress has been made in automatic speech recognition (ASR), significant
performance degradation still exists in distant talking scenarios due to significantly lower …

Speaker verification in real-world applications sometimes deals with limited duration of
enrollment and/or test data. MFCC-based i-vector systems have defined the state-of-the-art …