The Multimodal Video Search by Examples (MVSE) project investigates usin...
A crucial part of an accurate and reliable spoken language assessment sy...
ASR error correction continues to serve as an important part of
post-pro...
As speech recognition model sizes and training data requirements grow, i...
Error correction models form an important part of Automatic Speech
Recog...
ASR model deployment environment is ever-changing, and the incoming spee...
An end-to-end (E2E) speech recognition model implicitly learns a biased
...
This paper describes the AISpeech-SJTU system for the accent identificat...
Recently, pre-trained language models like BERT have shown promising
per...
One daunting problem for semantic parsing is the scarcity of annotation....
Traditional slot filling in natural language understanding (NLU) predict...