274 citations · 649 across the 26 of their papers we have counts for
26 papers
Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends
Xingyu Shen, Runze Wang, Wei-Ping Zhu +1
Speech enhancement is often used as a front-end for robust ASR, yet recurrent temporal and cross-band modules introduce sequential dependencies that reduce parallel efficiency. In…
Energy-Efficient D2D-Aided Fog Computing under Probabilistic Time Constraints
Onur Karatalay, Ioannis Psaromiligkos, Benoit Champagne
Device-to-device (D2D) communication is an enabling technology for fog computing by allowing the sharing of computation resources between mobile devices. However, temperature varia…
Channel Estimation for Hybrid Massive MIMO Systems with Adaptive-Resolution ADCs
Yalin Wang, Xihan Chen, Yunlong Cai +2
Achieving high channel estimation accuracy and reducing hardware cost as well as power dissipation constitute substantial challenges in the design of massive multiple-input multipl…
Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition
Arya Aftab, Alireza Morsali, Shahrokh Ghaemmaghami +1
Detecting emotions directly from a speech signal plays an important role in effective human-computer interactions. Existing speech emotion recognition models require massive comput…
Deep-Unfolding Neural-Network Aided Hybrid Beamforming Based on Symbol-Error Probability Minimization
S. Shi, Y. Cai, Q. Hu +2
In massive multiple-input multiple-output (MIMO) systems, hybrid analog-digital (AD) beamforming can be used to attain a high directional gain without requiring a dedicated radio f…
Deep Learning Framework for Hybrid Analog-Digital Signal Processing in mmWave Massive-MIMO Systems
Alireza Morsali, Afshin Haghighat, Benoit Champagne
Hybrid analog-digital signal processing (HSP) is an enabling technology to harvest the potential of millimeter-wave (mmWave) massive-MIMO communications. In this paper, we present…