Point to the Hidden: Exposing Speech Audio Splicing via Signal Pointer Nets

Moussa D, Hirsch G, Wankerl S, Rieß C (2023)


Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2023

Pages Range: 5057 - 5061

Conference Proceedings Title: Proc. INTERSPEECH 2023

Event location: Dublin IE

URI: https://faui1-files.cs.fau.de/public/publications/mmsec/2023-Moussa-Interspeech.pdf

DOI: 10.21437/Interspeech.2023-996

Abstract

Verifying the integrity of voice recording evidence for criminal investigations is an integral part of an audio  forensic analyst’s work. Here, one focus is on detecting deletion or insertion operations, so called audio splicing.  While this is a rather easy approach to alter spoken statements, careful editing can yield quite convincing results. For difficult cases or big amounts of data, automated tools can support in detecting potential editing locations. To this end, several analytical and deep learning methods have been proposed by now. Still, few address unconstrained splicing scenarios as expected in practice. With SigPointer, we propose a pointer network framework for continuous input that uncovers splice locations naturally and more efficiently than existing works.  Extensive experiments on forensically challenging data like strongly compressed and noisy signals quantify the benefit of the pointer mechanism with performance increases between about 6 to 10 percentage points.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Moussa, D., Hirsch, G., Wankerl, S., & Rieß, C. (2023). Point to the Hidden: Exposing Speech Audio Splicing via Signal Pointer Nets. In ISCA (Eds.), Proc. INTERSPEECH 2023 (pp. 5057 - 5061). Dublin, IE.

MLA:

Moussa, Denise, et al. "Point to the Hidden: Exposing Speech Audio Splicing via Signal Pointer Nets." Proceedings of the Interspeech 2023, 24th Annual Conference of the International Speech Communication Association, Dublin Ed. ISCA, 2023. 5057 - 5061.

BibTeX: Download