Florian Eyben — accepted AI-conference papers

2023

Masking Speech Contents by Random Splicing: is Emotional Expression Preserved?

Felix Burkhardt, Anna Derington, Matthias Kahlau, Klaus R. Scherer, Florian Eyben, Björn W. Schuller

ICASSP 2023accepted

We discuss the influence of random splicing on the perception of emotional expression in speech signals. Random splicing is the randomized reconstruction of short audio snippets with the aim to obfuscate the speech contents. A part of the German parliament recordings has been random spliced and both…

Cited by 0 Source ↗Scholar ↗

2017

Automatic multi-lingual arousal detection from voice applied to real product testing applications

Florian Eyben, Matthias Unfried, Gerhard Hagerer, Björn W. Schuller

ICASSP 2017accepted

A method is presented which applies Long Short-Term Memory Recurrent Neural Networks on real market-research voice recordings in order to automatically predict emotional arousal from speech. While most previous work has dealt with evaluations of algorithms within the same speech corpus, the novelty…

Cited by 6 Source ↗Scholar ↗

2015

A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks

Erik Marchi, Fabio Vesperini, Florian Eyben, Stefano Squartini, Björn W. Schuller

ICASSP 2015accepted

Acoustic novelty detection aims at identifying abnormal/novel acoustic signals which differ from the reference/normal data that the system was trained with. In this paper we present a novel unsupervised approach based on a denoising autoencoder. In our approach auditory spectral features are process…

Cited by 0 Source ↗Scholar ↗