On the Detection of Pitch-Shifted Voice: Machines and Human Listeners

We present a performance comparison between human listeners and a simple algorithm for the task of speech anomaly detection. The algorithm utilises an intentionally small set of features derived from the source-filter model, with the aim of validating that key components of source-filter theory char...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5804 - 5808
Main Authors Looney, David, Gaubitch, Nikolay D.
Format Conference Proceeding
LanguageEnglish
Published IEEE 06.06.2021
Subjects
fraud
Signal processing algorithms
Software
Software algorithms
Software reliability
source-filter model
Speech processing
Support vector machines
Task analysis
voice modification
Online AccessGet full text

Cover

More Information
Summary:We present a performance comparison between human listeners and a simple algorithm for the task of speech anomaly detection. The algorithm utilises an intentionally small set of features derived from the source-filter model, with the aim of validating that key components of source-filter theory characterise how humans perceive anomalies. We furthermore recognise that humans are adept at detecting anomalies without prior exposure to a given anomaly class. To that end, we also consider the algorithm performance when operating via the principle of unsupervised learning where a null model is derived from normal speech recordings. We evaluate both the algorithm and human listeners for pitch-shift detection where the pitch of a speech sample is intentionally modified using software, a phenomenon of relevance to the fields of fraud detection and forensics. Our results show that humans can only detect pitch-shift reliably at more extreme levels, and that the performance of the algorithm matches closely with that of humans.
ISSN:2379-190X
DOI:10.1109/ICASSP39728.2021.9414890