In recent years, neural models learned through self-supervised pretraining on large scale
multilingual text or speech data have exhibited promising results for underresourced …

" Transcription bottlenecks", created by a shortage of effective human transcribers are one of
the main challenges to endangered language (EL) documentation. Automatic speech …

This paper describes the process of data processing and training of an automatic speech
recognition (ASR) system for Cook Islands Māori (CIM), an Indigenous language spoken by …

This paper reports on progress integrating the speech recognition toolkit ESPnet into Elpis, a
web front-end originally designed to provide access to the Kaldi automatic speech …

More than 85% of the languages spoken in Canada are deemed as vulnerable (Lewis,
2009). Efforts for language revitalization and maintenance are essential to maintain both the …

Our study presents a series of experiments on speech recognition with endangered and
extinct Samoyedic languages, spoken in Northern and Southern Siberia. To best of our …

Linguistic tone is transcribed for input into ASR systems in numerous ways. This paper
shows a systematic test of several transcription styles, using as an example the Chibchan …

Big languages such as English and Finnish have many natural language processing (NLP)
resources and models, but this is not the case for low-resourced and endangered languages …

This paper describes three open access Yoloxóchitl Mixtec corpora and presents the results
and implications of end-to-end automatic speech recognition for endangered language …

In this paper, we investigate the effect of layer freezing on the effectiveness of model transfer
in the area of automatic speech recognition. We experiment with Mozilla's Deep-Speech …