A new dataset enhances speech synthesis by capturing emotional expression without relying on text.
― 5 min read
Yossi Adi
Examining the relationship between transformers and RNNs in language processing.
― 7 min read
Introducing Discrete Flow Matching for better discrete data generation techniques.
― 3 min read
New watermarking methods protect creators in audio generative models.
― 4 min read