Browsing Institutt for elektroniske systemer by Author "Gelderblom, Femke B."
Now showing items 1-4 of 4
-
Deep Complex Convolutional Recurrent Network for Multi-Channel Speech Enhancement and Dereverberation
Gelderblom, Femke B.; Myrvoll, Tor Andre (Chapter, 2021)This paper proposes a neural network based system for multi-channel speech enhancement and dereverberation. Speech recorded indoors by a far field microphone, is invariably degraded by noise and reflections. Recent single ... -
Evaluating Performance Metrics for Deep Neural Network-based Speech Enhancement Systems
Gelderblom, Femke B. (Doctoral theses at NTNU;2023:53, Doctoral thesis, 2023)A recurring challenge for speech enhancement (SE) systems, is that removing/reducing noise and reverberance does not necessarily increase the intelligibility or the quality of the speech for human listeners. Deep neural ... -
Subjective Intelligibility of Deep Neural Network-Based Speech Enhancement
Gelderblom, Femke B.; Tronstad, Tron Vedul; Viggen, Erlend Magnus (Journal article; Peer reviewed, 2017)Recent literature indicates increasing interest in deep neural networks for use in speech enhancement systems. Currently, these systems are mostly evaluated through objective measures of speech quality and/or intelligibility. ... -
SYNTHETIC DATA FOR DNN-BASED DOA ESTIMATION OF INDOOR SPEECH
Gelderblom, Femke B.; Kvam, Johannes; Liu, Yi; Myrvoll, Tor Andre (Chapter, 2021)This paper investigates the use of different room impulse response (RIR) simulation methods for synthesizing training data for deep neural network-based direction of arrival (DOA) estimation of speech in reverberant rooms. ...