Over the past decades, a tremendous amount of research has been done on the use of
machine learning for speech processing applications, especially speech recognition …

With advancements of wireless and sensing technologies, recent studies have
demonstrated technical feasibility and effectiveness of using acoustic signals for sensing. In …

CHiME-3 is a research community challenge organised in 2015 to evaluate speech
recognition systems for mobile multi-microphone devices used in noisy daily environments …

This paper proposes a simple yet effective model-based neural network speaker adaptation
technique that learns speaker-specific hidden unit contributions given adaptation data …

This work presents a broad study on the adaptation of neural network acoustic models by
means of learning hidden unit contributions (LHUC)-a method that linearly re-combines …

In this paper we search for an optimal strategy for semi-supervised Deep Neural Network
(DNN) training. We assume that a small part of the data is transcribed, while the majority of …

Automatic recognition of disordered and elderly speech remains a highly challenging task to
date due to the difficulty in collecting such data in large quantities. This paper explores a …

Recent studies have confirmed that attention mechanisms with location constraint strategy
are helpful to reduce the misrecognition caused by incorrect alignments in attention-based …

With increasing global demand for learning English as a second language, there has been
considerable interest in methods of automatic assessment of spoken language proficiency …

In the past, conventional i-vectors based on a Universal Background Model (UBM) have
been successfully used as input features to adapt a Deep Neural Network (DNN) Acoustic …