This paper proposes a direct text to speech translation system using dis...
Research in multilingual speech-to-text translation is topical. Having a...
Recent models such as XLS-R and Whisper have made multilingual speech
te...
Pseudo-label (PL) filtering forms a crucial part of Self-Training (ST)
m...
We propose the SAMU-XLSR: Semantically-Aligned Multimodal Utterance-leve...
We propose a simple and effective cross-lingual transfer learning method...
Recent work on speech self-supervised learning (speech SSL) demonstrated...
The performance of automatic speech recognition (ASR) systems typically
...
More than half of the 7,000 languages in the world are in imminent dange...
Probabilistic Latent Variable Models (LVMs) provide an alternative to
se...
In this paper we demonstrate methods for reliable and efficient training...
We present the speech to text transcription system, called DARTS, for lo...
We investigate different approaches for dialect identification in Arabic...