Abstract Automatic Speech Recognition has reached almost human performance in some
controlled scenarios. However, recognition of impaired speech is a difficult task for two main …

Incorporating automatic speech recognition (ASR) in individualized speech training
applications is becoming more viable thanks to the improved generalization capabilities of …

This paper describes the investigation of the use of the deep neural networks (DNN) for the
detection of pathological speech. The state-of-the-art VGG16 convolutional neural network …

This paper investigates the ability of deep neural networks (DNNs) to improve the automatic
recognition of dysarthric speech through the use of convolutional neural networks (CNNs) …

Research on automatic speech recognition (ASR) of pathological speech is particularly
hindered by scarce in-domain data resources. Collecting representative pathological …

In this paper, we propose and investigate a variety of distributed deep learning strategies for
automatic speech recognition (ASR) and evaluate them with a state-of-the-art Long short …

This paper describes IDEA a database of Italian dysarthric speech produced by 45 speakers
affected by 8 different pathologies. Neurologic diagnoses were collected from the subjects' …

Dysarthria is a motor speech disorder, resulting in mumbled, slurred or slow speech that is
generally difficult to understand by both humans and machines. Traditional Automatic …

Nowadays, many application scenarios benefit from automatic speech recognition (ASR)
technology. Within the field of speech therapy, in some cases ASR is exploited in the …

This paper presents an implementation of an ASR system for the Romanian language that
uses a multi-layer neural network architecture to transcribe the input speech, augmented …