Johannes Kvam — accepted AI-conference papers

2021

Synthetic Data For Dnn-Based Doa Estimation of Indoor Speech

Femke B. Gelderblom, Yi Liu, Johannes Kvam, Tor André Myrvoll

ICASSP 2021accepted

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.Different sets of synthetic RIRs are obtained using the image source method (I…

Cited by 0 Source ↗Scholar ↗

2020

Principal Feature Visualisation in Convolutional Neural Networks

Marianne Bakken, Johannes Kvam, Alexey A. Stepanov, Asbjørn Berge

ECCV 2020poster

We introduce a new visualisation technique for CNNs called Principal Feature Visualisation (PFV). It uses a single forward pass of the original network to map principal features from the final convolutional layer to the original image space as RGB channels. By working on a batch of images we can ext…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗