Large self-supervised pre-trained speech models require computationally
...
Despite recent strides made in Speech Separation, most models are traine...
In this paper, we propose ACA-Net, a lightweight, global context-aware
s...
Most of the existing neural-based models for keyword spotting (KWS) in s...
Learning on a massive amount of speech corpus leads to the recent succes...
Existing self-supervised pre-trained speech models have offered an effec...
Noise robustness in keyword spotting remains a challenge as many models ...
It is critical for a keyword spotting model to have a small footprint as...
Building efficient architecture in neural speech processing is paramount...
Learning information-rich and generalizable representations effectively ...