research
∙
06/14/2023
When to Use Efficient Self Attention? Profiling Text, Speech and Image Transformer Variants
We present the first unified study of the efficiency of self-attention-b...
share
research
∙
05/24/2023
Unit-based Speech-to-Speech Translation Without Parallel Data
We propose an unsupervised speech-to-speech translation (S2ST) system th...
research
∙
12/02/2022
Continual Learning for On-Device Speech Recognition using Disentangled Conformers
Automatic speech recognition research focuses on training and evaluating...
research
∙
11/03/2022
Zero-shot Video Moment Retrieval With Off-the-Shelf Models
For the majority of the machine learning community, the expensive nature...
research
∙
11/01/2022
Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality
Recent visuolinguistic pre-trained models show promising progress on var...
research
∙
04/01/2021
Multilingual and code-switching ASR challenges for low resource Indian languages
Recently, there is increasing interest in multilingual automatic speech ...
research
∙
10/19/2020