Effect of identical twins on deep speaker embeddings based forensic voice comparison

Deep learning has gained widespread adoption in forensic voice comparison in recent years. It is mainly used to learn speaker representations, known as embedding features or vectors. In this work, the effect of identical twins on two state-of-the-art deep speaker embedding methods was investigated w...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of speech technology Vol. 27; no. 2; pp. 341 - 351
Main Authors Abed, Mohammed Hamzah, Sztahó, Dávid
Format Journal Article
LanguageEnglish
Published New York Springer US 2024
Springer Nature B.V
Subjects
Artificial Intelligence
Deep learning
Embedding
Engineering
Error analysis
Error reduction
Likelihood ratio
Signal,Image and Speech Processing
Social Sciences
Speaker identification
State vectors
Twins
Verification
Voice
Twins
Speaker verification
Forensic voice comparison
X-vectors
ECAPA-TDNN
Likelihood-ratio framework
Online AccessGet full text

Cover

More Information
Summary:Deep learning has gained widespread adoption in forensic voice comparison in recent years. It is mainly used to learn speaker representations, known as embedding features or vectors. In this work, the effect of identical twins on two state-of-the-art deep speaker embedding methods was investigated with special focus on metrics of forensic voice comparison. The speaker verification performance has been assessed using the likelihood-ratio framework by likelihood ratio cost and equal error rate. The AVTD twin speech dataset was applied. The results show a significant reduction in speaker verification performance when twin samples are present. Neither the adaptation of LR score calculation to twin samples, nor fine-tuning the pre-trained speaker embedding models seemed to be able to leverage this limitation. It was found that the recognition of same or different speakers was possible even in the case of identical twins but the performance dropped greatly. The lowest EER of the best performing model was 3.4% in the case of non-twin; at the same time, EER was 25.3% when twins were present. This doesn’t mean that the presented methods are useless in case of identical twins, but it must be taken into consideration that in case of a higher likelihood-ratio score (which indicates same speakers on the tested samples), the possibility of twins must also be considered in a real casework.
ISSN:1381-2416
1572-8110
DOI:10.1007/s10772-024-10108-6