Automatic Speech Recognition (ASR) has historically been a driving force behind many
machine learning (ML) techniques, including the ubiquitously used hidden Markov model …

Active learning is a label-efficient machine learning method that actively selects the most
valuable unlabeled samples to annotate. Active learning focuses on achieving the best …

While semi-supervised learning (SSL) has received tremendous attentions in many machine
learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either …

We propose a novel approach to semi-supervised automatic speech recognition (ASR). We
first exploit a large amount of unlabeled audio data via representation learning, where we …

Active learning is used for classification when labeling data are costly, while the main
challenge is to identify the critical instances that should be labeled. Clustering-based …

This paper presents an improved transfer learning framework applied to robust personalised
speech recognition models for speakers with dysarthria. As the baseline of transfer learning …

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 …

Only a few customers can be labeled in realistic credit-scoring problems, while many other
customers cannot. Further, satisfactory performance is difficult, as traditional supervised …

This paper examines the impact of multilingual (ML) acoustic representations on Automatic
Speech Recognition (ASR) and keyword search (KWS) for low resource languages in the …

One key issue for most classification algorithms is that they need large amounts of labeled
samples to train the classifier. Since manual labeling is time consuming, researchers have …