514 citations · 1.4k across the 79 of their papers we have counts for
4 papers · 1 filter
SoundChoice: Grapheme-to-Phoneme Models with Semantic Disambiguation
Artem Ploujnikov, Mirco Ravanelli
End-to-end speech synthesis models directly convert the input characters into an audio representation (e.g., spectrograms). Despite their impressive performance, such models have d…
Resource-Efficient Separation Transformer
Luca Della Libera, Cem Subakan, Mirco Ravanelli +3
Transformers have recently achieved state-of-the-art performance in speech separation. These models, however, are computationally demanding and require a lot of learnable parameter…
Learning Representations for New Sound Classes With Continual Self-Supervised Learning
Zhepei Wang, Cem Subakan, Xilin Jiang +4
In this paper, we work on a sound recognition system that continually incorporates new sound classes. Our main goal is to develop a framework where the model can be updated without…
Exploring Self-Attention Mechanisms for Speech Separation
Cem Subakan, Mirco Ravanelli, Samuele Cornell +2
Transformers have enabled impressive improvements in deep learning. They often outperform recurrent and convolutional models in many tasks while taking advantage of parallel proces…