The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

We study the capabilities of speech processing systems trained simply to predict large
amounts of transcripts of audio on the internet. When scaled to 680,000 hours of multilingual …

Motivated by the success of T5 (Text-To-Text Transfer Transformer) in pre-trained natural
language processing models, we propose a unified-modal SpeechT5 framework that …

We introduce VoxPopuli, a large-scale multilingual corpus providing 100K hours of
unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised …

We present a direct speech-to-speech translation (S2ST) model that translates speech from
one language to speech in another language without relying on intermediate text …

The remarkable success of transformers in the field of natural language processing has
sparked the interest of the speech-processing community, leading to an exploration of their …

Speech translation (ST) is an increasingly popular topic of research, partly due to the
development of benchmark datasets. Nevertheless, current datasets cover a limited number …

How to learn a better speech representation for end-to-end speech-to-text translation (ST)
with limited labeled data? Existing techniques often attempt to transfer powerful machine …

Speech emotion recognition (SER) classifies speech into emotion categories such as:
Happy, Angry, Sad and Neutral. Recently, deep learning has been applied to the SER task …

How can we learn unified representations for spoken utterances and their written text?
Learning similar representations for semantically similar speech and text is important for …