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

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Burkhardt, Felix, Derington, Anna, Kahlau, Matthias, Scherer, Klaus, Eyben, Florian, Schuller, Bjorn
Format: Conference Proceeding
Language:English
Subjects:
anonymization
emotional
Linguistics
Machine learning
masking
Prediction algorithms
Predictive models
random splicing
Signal processing algorithms
speech
Splicing
Transformers
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 versions - the original and the scrambled ones - manually labeled with respect to the arousal, valence and dominance dimensions. Additionally, we run a state-of-the-art transformer-based pre-trained emotional model on the data. We find sufficiently high correlation for the annotations and predictions of emotional dimensions between both sample versions to be confident that machine learners can be trained with random spliced data.
ISSN:2379-190X
DOI:10.1109/ICASSP49357.2023.10097094