Robust text-dependent speaker verification system using gender aware Siamese-Triplet Deep Neural Network
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study introduces a Gender-Aware Siamese-Triplet Network-Deep Neural Network (ST-DNN) for improved speaker verification. The novel architecture significantly reduces error rates, enhancing security in voice authentication systems.
Area Of Science
- Speech processing
- Machine learning
- Biometrics
Background
- Text-dependent speaker verification is crucial for security but challenged by voice variations.
- Existing methods struggle with linguistic diversity and gender-specific pitch differences, impacting accuracy.
Purpose Of The Study
- To introduce a Gender-Aware Siamese-Triplet Network-Deep Neural Network (ST-DNN) for enhanced speaker verification.
- To address challenges in speaker authentication caused by voice quality, linguistic diversity, and gender differences.
Main Methods
- Utilized Convolutional 2D layers with ReLU activation for feature extraction.
- Implemented multi-fusion dense skip connections and batch normalization for feature integration.
- Employed separate male and female ST-DNN models, incorporating Individual, Siamese, and Triplet Networks.
Main Results
- Achieved significant reductions in Equal Error Rate (EER) for males (32.31%–54.55%) and females (33.73%–38.98%).
- Demonstrated substantial reductions in Minimum Decision Cost Function (MinDCF) for males (53.47%–86.36%) and females (39.46%–71.19%).
- Validated the ST-DNN architecture's efficacy on RSR2015 and RedDots Challenge 2016 datasets.
Conclusions
- The Gender-Aware ST-DNN architecture effectively improves text-dependent speaker verification accuracy.
- The proposed method robustly handles variations in voice quality, linguistic diversity, and gender-specific characteristics.
- Results confirm the ST-DNN's suitability for real-world high-security voice authentication applications.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
The sign test for matched pairs offers a robust method for comparing two paired samples, often for the effects of an intervention in one of them. This method is very useful in situations where the underlying distribution of the data is unknown. The test compares two related samples—often pre- and post-treatment measurements on the same subjects—to determine if there are significant differences in their median values.
To conduct the sign test, we first calculate the differences in...
