Recently, the speech community is seeing a significant trend of moving from deep neural
network based hybrid modeling to end-to-end (E2E) modeling for automatic speech …

In the last decade of automatic speech recognition (ASR) research, the introduction of deep
learning has brought considerable reductions in word error rate of more than 50% relative …

Building ASR models across many languages is a challenging multi-task learning problem
due to large variations and heavily unbalanced data. Existing work has shown positive …

The development of end-to-end models has largely sped up the research in massively
multilingual automatic speech recognition (MMASR). Previous research has demonstrated …

Automatic Speech Recognition (ASR) systems are often optimized to work best for speakers
with canonical speech patterns. Unfortunately, these systems perform poorly when tested on …

Background Eating disorders affect an increasing number of people. Social networks
provide information that can help. Objective We aimed to find machine learning models …

We improve on the popular conformer architecture by replacing the depthwise temporal
convolutions with diagonal state space (DSS) models. DSS is a recently introduced variant …

In our previous work we demonstrated that a single headed attention encoder-decoder
model is able to reach state-of-the-art results in conversational speech recognition. In this …

Neural transducers have been widely used in automatic speech recognition (ASR). In this
paper, we introduce it to streaming end-to-end speech translation (ST), which aims to …

Compared to hybrid automatic speech recognition (ASR) systems that use a modular
architecture in which each component can be in-dependently adapted to a new domain …