New scheme based on GMM-PCA-SVM modelling for automatic speaker recognition

Zergat, Kawthar Yasmine; Amrouche, Abderrahmane

doi:10.1007/s10772-014-9235-7

Cited by 13 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the previous work, the traditional features such as MFCC [27], Gaussian statistical characteristics [15] were often applied to speaker identification, which had good performance. In this paper, we extract 48-dimension MFCC from the input speech and calculate the Gaussian statistics as the input feature to train the SVM.…”

Section: Recombined Gaussian Supervectormentioning

confidence: 99%

“…MFCC represents the transient power range of human speech [15]. Mel frequency reflects the conversion relationship between actual frequency and perceptual frequency.…”

Section: Mfccmentioning

confidence: 99%

“…It could effectively reduce the consumption of computer hardware. There were also some classical models such as Gaussian Mixture Model (GMM)-Support Vector Machine (GMM-SVM) [15], GMM-Universal Background Model (GMM-UBM) [16] and Probabilistic Linear Discriminant Analysis/i-vector (PLDA/ivector) [17] applied to speaker recognition. In recent years, more and more researchers have used deep networks to complete speaker recognition.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Speaker Recognition Based on Fusion of a Deep and Shallow Recombination Gaussian Supervector

Sun

Zou

et al. 2020

Electronics

View full text Add to dashboard Cite

Extracting speaker’s personalized feature parameters is vital for speaker recognition. Only one kind of feature cannot fully reflect the speaker’s personality information. In order to represent the speaker’s identity more comprehensively and improve speaker recognition rate, we propose a speaker recognition method based on the fusion feature of a deep and shallow recombination Gaussian supervector. In this method, the deep bottleneck features are first extracted by Deep Neural Network (DNN), which are used for the input of the Gaussian Mixture Model (GMM) to obtain the deep Gaussian supervector. On the other hand, we input the Mel-Frequency Cepstral Coefficient (MFCC) to GMM directly to extract the traditional Gaussian supervector. Finally, the two categories of features are combined in the form of horizontal dimension augmentation. In addition, when the number of speakers to be recognized increases, in order to prevent the system recognition rate from falling sharply, we introduce the optimization algorithm to find the optimal weight before the feature fusion. The experiment results indicate that the speaker recognition rate based on the feature which is fused directly can reach 98.75%, which is 5% and 0.62% higher than the traditional feature and deep bottleneck feature, respectively. When the number of speakers increases, the fusion feature based on optimized weight coefficients can improve the recognition rate by 0.81%. It is validated that our proposed fusion method can effectively consider the complementarity of the different types of features and improve the speaker recognition rate.

show abstract

Section: Recombined Gaussian Supervectormentioning

confidence: 99%

“…MFCC represents the transient power range of human speech [15]. Mel frequency reflects the conversion relationship between actual frequency and perceptual frequency.…”

Section: Mfccmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Speaker Recognition Based on Fusion of a Deep and Shallow Recombination Gaussian Supervector

Sun

Zou

et al. 2020

Electronics

View full text Add to dashboard Cite

show abstract

“…For digital speech signals, there are a lot of research results in speech enhancement (Shima, Ahmad, & Babak, 2015;Ji & Danny, 2014;Mohamed & Pascal, 2014;Belinda & Kuldip, 2014;Seon & Hong, 2014) and speaker recognition (Shiha, Linb, Wanga, & Lina, 2011;Srikanth, 2014, pp. 137-145;Kawthar & Abderrahmane, 2014;Khan, Baig, & Youssef, 2010). However the speech content authentication schemes are rare.…”

Section: Introductionmentioning

confidence: 99%

A Secure Speech Content Authentication Algorithm Based on Discrete Fractional Fourier Transform

Wang

Zhang

Liu

2015

International Journal of Digital Crime and Forensics

View full text Add to dashboard Cite

Watermark schemes content-based provide one way to solve the veracity and integrity of speech content. Some existed content-based schemes are vulnerable to feature-analysed substitution attack. Aiming to solve the problems, a secure speech content authentication algorithm is proposed, on the basic of the undeterminate angle of discrete fractional fourier transform. In the paper, the definition and calculation of discrete fractional fourier transform are given. And the watermark generation method based on discrete fractional fourier transform is analyzed. Frame number and watermark bits are embedded into hybrid domain of scrambled signals. Compared with the existed watermark schemes, the features for watermark generation and embedding are secret, which improves the security of watermark system. Theoretical analysis and experimental evaluation results show that the proposed algorithm is inaudible, robust to desynchronous attacks and has the excellent ability of tamper detection and tamper location.

show abstract