End-to-end (E2E) multi-channel ASR systems show state-of-the-art perform...
In this paper, we propose a dual-encoder ASR architecture for joint mode...
Automatic speech-based affect recognition of individuals in dyadic
conve...
A common problem in machine learning is to deal with datasets with disjo...
In this paper, we apply Semi-Supervised Learning (SSL) along with Data
A...
Sequence-to-sequence (seq2seq) based ASR systems have shown state-of-the...
Transcription of broadcast news is an interesting and challenging applic...
Model-based methods and deep neural networks have both been tremendously...