There is a wide variety of speech processing tasks ranging from extracti...
Self-supervised learning (SSL) has proven vital for advancing research i...
Speech separation has been well-developed while there are still problems...
Videos uploaded on social media are often accompanied with textual
descr...
Producing a large annotated speech corpus for training ASR systems remai...
Unsupervised discovery of acoustic tokens from audio corpora without
ann...
Recurrent neural networks (RNNs) have achieved great success in language...