Search Results for author:
Found 2 papers, 1 papers with code
CycleGAN-Based Unpaired Speech Dereverberation
Typically, neural network-based speech dereverberation models are trained on paired data, composed of a dry utterance and its corresponding reverberant utterance.
Towards Learning a Universal Non-Semantic Representation of Speech
The ultimate goal of transfer learning is to reduce labeled data requirements by exploiting a pre-existing embedding model trained for different datasets or tasks.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
