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 …

How to leverage dynamic contextual information in end-to-end speech recognition has
remained an active research area. Previous solutions to this problem were either designed …

The problem of machine learning systems demonstrating bias towards specific groups of
individuals has been studied extensively, particularly in the Facial Recognition area, but …

In this study, we present recent developments of models trained with the RNN-T loss in
ESPnet. It involves the use of various archi-tectures such as recently proposed Conformer …

We propose a novel method to accelerate training and inference process of recurrent neural
network transducer (RNN-T) based on the guidance from a co-trained connectionist …

With 4.5 million hours of English speech from 10 different sources across 120 countries and
models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech …

End-to-end automatic speech recognition (ASR) has become an increasingly popular area
of research, with two main models being online and offline ASR. Online models aim to …

Word Error Rate (WER) has been the predominant metric used to evaluate the performance
of automatic speech recognition (ASR) systems. However, WER is sometimes not a good …

As speech-enabled devices such as smartphones and smart speakers become increasingly
ubiquitous, there is growing interest in building automatic speech recognition (ASR) systems …

Attention-based contextual biasing approaches have shown significant improvements in the
recognition of generic and/or personal rare-words in End-to-End Automatic Speech …