Neural Machine Translation (NMT) has seen tremendous growth in the last ten years since
the early 2000s and has already entered a mature phase. While considered the most widely …

After generations of exploitation, Indigenous people often respond negatively to the idea that
their languages are data ready for the taking. By treating Indigenous knowledge as a …

Recently great strides have been made in the field of automatic speech recognition (ASR) by
using various deep learning techniques. In this study, we present a thorough comparison …

When we first started planning to write a book on how people would be able to talk in a
natural way to their smartphones, devices and robots, we could not have anticipated that the …

Training a conventional automatic speech recognition (ASR) system to support multiple
languages is challenging because the sub-word unit, lexicon and word inventories are …

All language is characterised by variation which language users employ to construct
complex social identities and express social meaning. Like other machine learning …

In the last decades, several systems based on video analysis have been proposed for
automatically detecting accidents on roads to ensure a quick intervention of emergency …

NLP research is impeded by a lack of resources and awareness of the challenges presented
by underrepresented languages and dialects. Focusing on the languages spoken in …

End-to-end automatic speech recognition (ASR) can significantly reduce the burden of
developing ASR systems for new languages, by eliminating the need for linguistic …

Sequence-to-sequence (seq2seq) approach for low-resource ASR is a relatively new
direction in speech research. The approach benefits by performing model training without …