Modern Automatic Speech Recognition (ASR) systems often use a portfolio ...
Comprehending the overall intent of an utterance helps a listener recogn...
Accents mismatching is a critical problem for end-to-end ASR. This paper...
Semi-supervised learning (SSL) is an active area of research which aims ...
Multilingual ASR technology simplifies model training and deployment, bu...
Building conversational speech recognition systems for new languages is
...