activity
20182021
most citedExploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks

43 citations · 46 across the 4 of their papers we have counts for

collaborators

7 papers

cs.CV2021

DNN Quantization with Attention

Ghouthi Boukli Hacene, Lukas Mauch, Stefan Uhlich +1

Low-bit quantization of network weights and activations can drastically reduce the memory footprint, complexity, energy consumption and latency of Deep Neural Networks (DNNs). Howe…

eess.AS2020

Unsupervised Cross-Domain Speech-to-Speech Conversion with Time-Frequency Consistency

Mohammad Asif Khan, Fabien Cardinaux, Stefan Uhlich +2

In recent years generative adversarial network (GAN) based models have been successfully applied for unsupervised speech-to-speech conversion.The rich compact harmonic view of the…

eess.AS202043 cited

Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks

Yuichiro Koyama, Tyler Vuong, Stefan Uhlich +1

Recently, deep neural networks (DNNs) have been successfully used for speech enhancement, and DNN-based speech enhancement is becoming an attractive research area. While time-frequ…

eess.AS20193 cited

Closing the Training/Inference Gap for Deep Attractor Networks

Cyril Cadoux, Stefan Uhlich, Marc Ferras +1

This paper improves the deep attractor network (DANet) approach by closing its gap between training and inference. During training, DANet relies on attractors, which are computed f…

cs.LG2019

Mixed Precision DNNs: All you need is a good parametrization

Stefan Uhlich, Lukas Mauch, Fabien Cardinaux +5

Efficient deep neural network (DNN) inference on mobile or embedded devices typically involves quantization of the network parameters and activations. In particular, mixed precisio…

cs.LG2018

Iteratively Training Look-Up Tables for Network Quantization

Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama +4

Operating deep neural networks on devices with limited resources requires the reduction of their memory footprints and computational requirements. In this paper we introduce a trai…