We propose two approaches to handle speech recognition for task domains with sparse
matched training data. One is an active learning method that selects training data for the …

Negative transfer in training of acoustic models for automatic speech recognition has been
reported in several contexts such as domain change or speaker characteristics. This paper …

In this work, we investigate a machine learning approach to cost-effectively train acoustic
models for speech recognition. More specifically, we utilize an active learning method that …

We propose an acoustic model training method which combines committee-based active
learning and semi-supervised learning for large vocabulary continuous speech recognition …

State-of-the-art speech recognition systems are trained using human transcriptions of
speech utterances. In this paper, we describe a method to combine active and unsupervised …

Although there have been regular improvements in speech recognition technology over the
past decade, speech recognition is far from being a solved problem. Recognition systems …

It is challenging to obtain large amounts of native (matched) labels for audio in under-
resourced languages. This could be due to a lack of literate speakers of the language or a …

The last decade has witnessed major advances in core speech recognition technology, with
today's systems able to recognize continuous speech from many speakers without the need …

Recently developed end-to-end (E2E) automatic speech recognition (ASR) systems demand
abundance of transcribed speech data, there are several scenarios where the labeling of …

With the recent developments of highly parametric deep learning architectures, many recent
works have demonstrated their effectiveness with End-to-End approaches in achieving state …