On the fusion of dissimilarity-based classifiers for speaker identification

Kinnunen, Tomi; Hautamäki, Ville; Fränti, Pasi

doi:10.21437/eurospeech.2003-721

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fusing occurs following the fusion of personal features after matching fusion. This comprises the following fusion levels: rank level fusion, match decision level fusion, and score level fusion that can gives good accuracy between 92 and 96%, for more information details you can find it in [9][10][11][12][13][14][15][16][17].…”

Section: Related Wordmentioning

confidence: 99%

Performance of Multimodal Biometric Systems Using Face and Fingerprints (Short Survey)

Abdul-Al

Kyeremeh

Parchin

et al. 2021

2021 IEEE 26th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)

View full text Add to dashboard Cite

Biometric authentication is the science and engineering of assessing and evaluating bioinformatics from the human body in order to increase system security by providing reliable and accurate behaviors and classifiers for personal identification and authentication. Its solutions are widely used in industries, governments, and the military. This paper reviews the multimodal biometric systems that integrated both faces and fingerprints as well as shows which one has the best accuracy and hardware complexity with the methods and databases. Several methods have been used in multimodal biometric systems such as KNN (K-Nearest Neighbor), CNN (Convolutional Neural Network), PCA (Principal Component Analysis), and so on. A multimodal biometric system for face and fingerprints that uses an FoM (Figure of Merit) to compare and show between the articles the best accuracy that have used multimodal biometric system face and fingerprints methods. The best performance has been found is 99.43% by using the cascade multimodal method.

show abstract

Section: Related Wordmentioning

confidence: 99%

Performance of Multimodal Biometric Systems Using Face and Fingerprints (Short Survey)

Abdul-Al

Kyeremeh

Parchin

et al. 2021

2021 IEEE 26th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD)

View full text Add to dashboard Cite

show abstract

Evaluation of Speech Emotion Classification Based on GMM and Data Fusion

Vondra

Vích

2009

Cross-Modal Analysis of Speech, Gestures, Gaze and Facial Expressions

View full text Add to dashboard Cite

Limited data speaker identification

Jayanna

Prasanna

2010

Sadhana

View full text Add to dashboard Cite

In this paper, the task of identifying the speaker using limited training and testing data is addressed. Speaker identification system is viewed as four stages namely, analysis, feature extraction, modelling and testing. The speaker identification performance depends on the techniques employed in these stages. As demonstrated by different experiments, in case of limited training and testing data condition, owing to less data, existing techniques in each stage will not provide good performance. This work demonstrates the following: multiple frame size and rate (MFSR) analysis provides improvement in the analysis stage, combination of mel frequency cepstral coefficients (MFCC), its temporal derivatives ( , ), linear prediction residual (LPR) and linear prediction residual phase (LPRP) features provides improvement in the feature extraction stage and combination of learning vector quantization (LVQ) and gaussian mixture model -universal background model (GMM-UBM) provides improvement in the modelling stage. The performance is further improved by integrating the proposed techniques at the respective stages and combining the evidences from them at the testing stage. To achieve this, we propose strength voting (SV), weighted borda count (WBC) and supporting systems (SS) as combining methods at the abstract, rank and measurement levels, respectively. Finally, the proposed hierarchical combination (HC) method integrating these three methods provides significant improvement in the performance. Based on these explorations, this work proposes a scheme for speaker identification under limited training and testing data.

show abstract

On the fusion of dissimilarity-based classifiers for speaker identification

Cited by 4 publications

References 15 publications

Performance of Multimodal Biometric Systems Using Face and Fingerprints (Short Survey)

Performance of Multimodal Biometric Systems Using Face and Fingerprints (Short Survey)

Evaluation of Speech Emotion Classification Based on GMM and Data Fusion

Limited data speaker identification

Contact Info

Product

Resources

About