# Exploring the performance of automatic speaker recognition using twin speech and deep learning-based artificial neural networks

## TL;DR

This paper examines how well automatic speaker recognition systems can distinguish between identical twins and other speakers using different speech lengths and finds that twins are harder to differentiate.

## Contribution

The study introduces a novel evaluation of ASR performance with identical twin speakers using the SpeechBrain toolkit and varying speech lengths.

## Key findings

- Identical twins pose a significant challenge to automatic speaker recognition systems.
- Longer speech samples improve recognition accuracy and reduce variability in similarity estimates.
- Some twin pairs are more difficult for ASR systems to distinguish than others.

## Abstract

This study assessed the influence of speaker similarity and sample length on the performance of an automatic speaker recognition (ASR) system utilizing the SpeechBrain toolkit. The dataset comprised recordings from 20 male identical twin speakers engaged in spontaneous dialogues and interviews. Performance evaluations involved comparing identical twins, all speakers in the dataset (including twin pairs), and all speakers excluding twin pairs. Speech samples, ranging from 5 to 30 s, underwent assessment based on equal error rates (EER) and Log cost-likelihood ratios (Cllr). Results highlight the substantial challenge posed by identical twins to the ASR system, leading to a decrease in overall speaker recognition accuracy. Furthermore, analyses based on longer speech samples outperformed those using shorter samples. As sample size increased, standard deviation values for both intra and inter-speaker similarity scores decreased, indicating reduced variability in estimating speaker similarity/dissimilarity levels in longer speech stretches compared to shorter ones. The study also uncovered varying degrees of likeness among identical twins, with certain pairs presenting a greater challenge for ASR systems. These outcomes align with prior research and are discussed within the context of relevant literature.