Neural network-based language models are commonly used in rescoring
appr...
With the rapid development of speech assistants, adapting server-intende...
This paper presents an exploration of end-to-end automatic speech recogn...
Speaker diarization for real-life scenarios is an extremely challenging
...
Data augmentation is one of the most effective ways to make end-to-end
a...
While end-to-end ASR systems have proven competitive with the convention...
In this work we present simple grapheme-based system for low-resource sp...
This work proposes a novel approach to out-of-vocabulary (OOV) keyword s...