no code implementations • 7 Apr 2021 • Liu Chen, Meysam Asgari
A deep Transformer model with good evaluation score does not mean each subnetwork (a. k. a transformer block) learns reasonable representation.
no code implementations • 17 Nov 2020 • Liu Chen, Meysam Asgari
Building a high quality automatic speech recognition (ASR) system with limited training data has been a challenging task particularly for a narrow target population.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • WS 2020 • Yiyi Wang, Emily Prud{'}hommeaux, Meysam Asgari, Jill Dolata
We find that transfer learning improves scoring accuracy, particularly when using pretrained contextualized embeddings.
no code implementations • WS 2020 • Meysam Asgari, Liu Chen, Hiroko Dodge
Conversation is a complex cognitive task that engages multiple aspects of cognitive functions to remember the discussed topics, monitor the semantic and linguistic elements, and recognize others{'} emotions.