Login / Signup
MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation.
Shengkui Zhao
Yukun Ma
Chongjia Ni
Chong Zhang
Hao Wang
Trung Hieu Nguyen
Kun Zhou
Jia Qi Yip
Dianwen Ng
Bin Ma
Published in:
ICASSP (2024)
Keyphrases
</>
recurrent neural networks
recurrent networks
neural network
speech recognition
feed forward
frequency domain
artificial neural networks
fault diagnosis
fuzzy logic
speech signal
audio visual
power system
data sets
multi modal
denoising
nearest neighbor
spoken language
learning algorithm
endpoint detection