Eigen-MLLR coefficients as new feature parameters for speaker identification

Wang, Nick J.-C.; Tsai, Wei-Ho; Lee, Lin-Shan

doi:10.21437/eurospeech.2001-358

Cited by 6 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this research, MFCC+LBG can achieve better result compared with MFCC+DTW (15) and MFCC+GMM (Gaussian Mixture Model) (18) algorithms in both recognition accuracy and calculation burden. Performance results of these three algorithms with same chosen parameter (Section 4.3 point B's case) are indicated in Fig.…”

Section: Performance Comparisonmentioning

confidence: 86%

Human Activity Recognition from Environmental Background Sounds for Wireless Sensor Networks

2010

View full text Add to dashboard Cite

Non-memberTadahiro Kuroda ＊ Non-member Sound feature extraction Mel Frequency Cepstral Coefficients (MFCC) and Vector Quantization (VQ) classification Linde-Buzo-Gray algorithm (LBG) algorithms are applied for recognizing the background sounds in the human daily activities. Applying these algorithms to twenty typical daily activity sounds, average recognition accuracy of 93.8% can be achieved. In these algorithms, how three parameters (i.e., Mel filters number, frame-to-frame overlap and LBG codebook cluster number) affect system's calculation burden and accuracy is also investigated. By adjusting these three parameters to an optimized combination, the multiplication and addition calculation burden can be reduced by 87.0% and 87.1% individually while maintaining the system's average accuracy rate at 92.5%. This is promising for future integration with other sensor (s) to fulfill daily activity recognition by using power aware Wireless Sensor Networks (WSN) systems.

show abstract

Section: Performance Comparisonmentioning

confidence: 86%

Human Activity Recognition from Environmental Background Sounds for Wireless Sensor Networks

2010

View full text Add to dashboard Cite

show abstract

Speaker Modeling Technique Based on Regression Class for Speaker Identification with Sparse Training

Zhang

Zhao

2004

Advances in Biometric Person Authentication

View full text Add to dashboard Cite

Gmm-Based Bhattacharyya Kernel Fisher Discriminant Analysis For Speaker Recognition

Chao

Wang

Chang

Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.

View full text Add to dashboard Cite

Clearly, the linear discriminant classifier is not robust enough to cope with most real-world data classification problems. Kernel Fisher Discriminant Analysis (KFDA) tries to increase the expressiveness of the discriminant based on the high order statistics of the data set. In this paper, we propose the GMM-based KFDA with the Bhattacharyya kernel to obtain a transformation, or called a speaker eigenspace, based on which the transformed MFCC features are more discriminative for speaker recognition. In our approach, the eigenspace is directly constructed from the complete GMM parameter set, rather than the supervectors considering mean vectors only as the eigenvoice approach. Moreover, FDA, which is believed to be more appropriate for classification accuracy than Principal Component Analysis (PCA), is applied for eigenspace construction. The speaker identification experiments show that the new features outperform the MFCC features, in particular when the amount of enrollment data for each speaker is very small.

show abstract

Eigen-MLLR coefficients as new feature parameters for speaker identification

Cited by 6 publications

References 0 publications

Human Activity Recognition from Environmental Background Sounds for Wireless Sensor Networks

Human Activity Recognition from Environmental Background Sounds for Wireless Sensor Networks

Speaker Modeling Technique Based on Regression Class for Speaker Identification with Sparse Training

Gmm-Based Bhattacharyya Kernel Fisher Discriminant Analysis For Speaker Recognition

Contact Info

Product

Resources

About