We report on adaptation of multilingual end-to-end speech recognition models trained on as
many as 100 languages. Our findings shed light on the relative importance of similarity …

Cross-lingual transfer of knowledge from high-resource languages to low-resource
languages is an important research problem in automatic speech recognition (ASR). We …

Collecting labelled datasets for speech recognition systems for low-resource languages on
a diverse set of domains and speakers is expensive. In this work, we demonstrate an …

Generating accurate word-level transcripts of recorded speech for language documentation
is difficult and time-consuming, even for skilled speakers of the target language. Automatic …

This study proposes an innovative methodology to enhance the performance of multilingual
Automatic Speech Recognition (ASR) systems by capitalizing on the high semantic similarity …

Abstract Multilingual models for Automatic Speech Recognition (ASR) are attractive as they
have been shown to benefit from more training data, and better lend themselves to …

We summarize the accomplishments of a multi-disciplinary workshop exploring the
computational and scientific issues surrounding the discovery of linguistic units (subwords …

In this paper, various methodologies of acoustic and language models, as well as labeling
methods for automatic speech recognition for spoken dialogues in emergency call centers …

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 …

This paper proposes a new task for artificial intelligence. The image2speech task generates
a spoken description of an image. We present baseline experiments in which the neural net …