Cohort selection for text-dependent speaker verification score normalization

Khemiri, Houssemeddine; Petrovska‐Delacrétaz, Dijana

doi:10.1109/atsip.2016.7523167

Cited by 4 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most reliable and simplest form of normalization that is based on the estimation of mean and variance for the genuine or target speaker distribution is Z-norm [29]. The important highlight of the Z-norm is that it doesn't need to perform online permutations during the training process.…”

Section: Zero Normalization (Z-norm)mentioning

confidence: 99%

An improved normalized gain-based score normalization technique for spoof detection algorithm

Chadha

Abdullah

Angeline

2022

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

A spoof detection algorithm supports the speaker verification system to examine the false claims by an imposter through careful analysis of input test speech. The scores are employed to categorize the genuine and spoofed samples effectively. Under the mismatch conditions, the false acceptance ratio increases and can be reduced by appropriate score normalization techniques. In this article, we are using the normalized Discounted Cumulative Gain (nDCG) norm derived from ranking the speaker’s log-likelihood scores. The proposed scoring technique smoothens the decaying process due to logarithm with an added advantage from the ranking. The baseline spoof detection system employs Constant Q-Cepstral Co-efficient (CQCC) as the base features with a Gaussian Mixture Model (GMM) based classifier. The scores are computed using the ASVspoof 2019 dataset for normalized and without normalization conditions. The baseline techniques including the Zero normalization (Z-norm) and Test normalization (T-norm) are also considered. The proposed technique is found to perform better in terms of improved Equal Error Rate (EER) of 0.35 as against 0.43 for baseline system (no normalization) wrt to synthetic attacks using development data. Similarly, improvements are seen in the case of replay attack with EER of 7.83 for nDCG-norm and 9.87 with no normalization (no-norm). Furthermore, the tandem-Detection Cost Function (t-DCF) scores for synthetic attack are 0.015 for no-norm and 0.010 for proposed normalization. Additionally, for the replay attack the t-DCF scores are 0.195 for no-norm and 0.17 proposed normalization. The system performance is satisfactory when evaluated using evaluation data with EER of 8.96 for nDCG-norm as against 9.57 with no-norm for synthetic attacks while the EER of 9.79 for nDCG-norm as against 11.04 with no-norm for replay attacks. Supporting the EER, the t-DCF for nDCG-norm is 0.1989 and for no-norm is 0.2636 for synthetic attacks; while in case of replay attacks, the t-DCF is 0.2284 for the nDCG-norm and 0.2454 for no-norm. The proposed scoring technique is found to increase spoof detection accuracy and overall accuracy of speaker verification system.

show abstract

Section: Zero Normalization (Z-norm)mentioning

confidence: 99%

An improved normalized gain-based score normalization technique for spoof detection algorithm

Chadha

Abdullah

Angeline

2022

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

show abstract

“…A cohort speaker's set is one where different speakers utter the same prompt [3]. Here a four cohort speaker's set is considered.…”

Section: Cohort Set Preparationmentioning

confidence: 99%

“…In TD-SV system, the reference and the testing phrase are same. In this case, speakers speak the same text during the training and testing period [2], [3], [4], [5]. On the other hand, in TI-SV system there is no such bound [6].…”

Section: Introductionmentioning

confidence: 99%

Significance of Source Information for Text Dependent Speaker Verification

Hore¹,

Nirmala²,

Das³

et al. 2018

IJIGSP

View full text Add to dashboard Cite

This work focuses on text dependent speaker verification system where a source feature specifically residual Mel frequency cepstral coefficients (RMFCC), has been extracted in addition to a vocal tract system feature namely Mel frequency cepstral coefficients (MFCC). The RMFCC features are derived from the LP residuals whereas MFCC features are derived from the cepstral analysis of the speech signal. Thus, these two features have different information about the speaker. A four cohort speaker's set has been prepared using these two features and dynamic time warping (DTW) is used as the classifier. Performance comparison of the text dependent speaker verification model using MFCC and RMFCC features are enumerated. Experimental results shows that, using RMFCC feature alone do not give satisfactory results in comparison to MFCC. Also, the system's performance obtained using the MFCC features, is not optimum. So, to improve the performance of the system, these two features are combined together using different combination algorithms. The proposed lowest ranking method yields good performance with an equal error rate (EER) of 7.50%. To further improve the efficiency of the system, the proposed method is combined along with the strength voting and weighted ranking method in the hierarchical combination method to obtain an EER of 3.75%.

show abstract

An intrusion detection approach based on improved deep belief network

Tian

Han

et al. 2020

Appl Intell

View full text Add to dashboard Cite

Cohort selection for text-dependent speaker verification score normalization

Cited by 4 publications

References 10 publications

An improved normalized gain-based score normalization technique for spoof detection algorithm

An improved normalized gain-based score normalization technique for spoof detection algorithm

Significance of Source Information for Text Dependent Speaker Verification

An intrusion detection approach based on improved deep belief network

Contact Info

Product

Resources

About