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 …

This tutorial presents an overview of the progression of spoken language identification (LID)
systems and current developments. The introduction provides a background on automatic …

We propose a simple solution to use a single Neural Machine Translation (NMT) model to
translate between multiple languages. Our solution requires no changes to the model …

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 …

Speech processing for under-resourced languages is an active field of research, which has
experienced significant progress during the past decade. We propose, in this paper, a …

Communication has been an essential part of being human and living in society. There are
several different languages and variations of them, so you can speak English in one place …

It has long been speculated whether communication between humans and machines based
on natural speech related cortical activity is possible. Over the past decade, studies have …

We present two end-to-end models: Audio-to-Byte (A2B) and Byte-to-Audio (B2A), for
multilingual speech recognition and synthesis. Prior work has predominantly used …

Deaf people who use American Sign Language (ASL) are medically underserved and often
excluded from health research and surveillance. We used a community participatory …

This paper describes the advances in the multilingual text and speech database
GlobalPhone, a multilingual database of high-quality read speech with corresponding …