State-of-the-art neural network language models (NNLMs) represented by long short term
memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly …

Early diagnosis of Neurocognitive Disorder (NCD) is crucial in facilitating preventive care
and timely treatment to delay further progression. This paper presents the development of a …

A key task for speech recognition systems is to reduce the mismatch between training and
evaluation data that is often attributable to speaker differences. Speaker adaptation …

Discriminative training techniques define state-of-the-art performance for automatic speech
recognition systems. However, they are inherently prone to overfitting, leading to poor …

Automatic speech recognition (ASR) for disordered speech is a challenging task. People
with speech disorders such as dysarthria often have physical disabilities, leading to severe …

Pitch features have long been known to be useful for recognition of normal speech.
However, for disordered speech, the significant degradation of voice quality renders the …

Speaker verification systems usually suffer from the mismatch problem between training and
evaluation data, such as speaker population mismatch, the channel and environment …

Speech recognition technology is an important branch in the field of artificial intelligence,
aiming to transform human speech into computer-readable text information. However …

Effective and reliable monitoring and diagnostics of process control installations is of utmost
importance, as they are important part of world's economy. Detection of faulty behavior fits …

Discriminative training techniques define state-of-the-art performance for deep neural
networks (DNNs) based speech recognition systems across a wide range of tasks …