On the Use of MFCC Feature Vector Clustering for Efficient Text Dependent Speaker Recognition

2014 ◽  
pp. 305-312 ◽  
Author(s):  
Ankit Samal ◽  
Deebyadeep Parida ◽  
Mihir Ranjan Satapathy ◽  
Mihir Narayan Mohanty
Keyword(s):  
Speaker Recognition ◽  
Feature Vector ◽  
Vector Clustering

scholarly journals One Solution of Extension of Mel-Frequency Cepstral Coefficients Feature Vector for Automatic Speaker Recognition

2020 ◽  
Vol 49 (2) ◽  
pp. 224-236
Author(s):  
Ivan Jokić ◽  
Stevan Jokić ◽  
Vlado Delić ◽  
Zoran Perić
Keyword(s):  
Speaker Recognition ◽  
Speech Signal ◽  
Feature Vector ◽  
Main Idea ◽  
Decision Threshold ◽  
Mel Frequency Cepstral Coefficients ◽  
Automatic Speaker Recognition ◽  
Complex Models ◽  
Speech Spectrum ◽  
Cepstral Coefficients

One extension of feature vector for automatic speaker recognition is considered in this paper. The starting feature vector consisted of 18 mel-frequency cepstral coefficients (MFCCs). Extension was done with two additional features derived from the spectrum of the speech signal. The main idea that generated this research is that it is possible to increase the efficiency of automatic speaker recognition by constructing a feature vector which tracks a real perceived spectrum in the observed speech. Additional features are based on the energy maximums in the appropriate frequency ranges of observed speech frames. In experiments, accuracy and equal error rate (EER) are compared in the case when feature vectors contain only 18 MFCCs and in cases when additional features are used. Recognition accuracy increased by around 3%. Values of EER show smaller differentiation but the results show that adding proposed additional features produced a lower decision threshold. These results indicate that tracking of real occurrences in the spectrum of the speech signal leads to more efficient automatic speaker recognizer. Determining features which track real occurrences in the speech spectrum will improve the procedure of automatic speaker recognition and enable avoiding complex models.

Saliency-Driven Oil Tank Detection Based on Multidimensional Feature Vector Clustering for SAR Images

2019 ◽  
Vol 16 (4) ◽  
pp. 653-657 ◽  
Author(s):  
Libao Zhang ◽  
Shiyi Wang ◽  
Congyang Liu ◽  
Yue Wang
Keyword(s):  
Feature Vector ◽  
Sar Images ◽  
Oil Tank ◽  
Vector Clustering

Image Retrieval Based on Color-Statistic Feature

2013 ◽  
Vol 765-767 ◽  
pp. 1046-1049
Author(s):  
Jin Mei Liu ◽  
Ji Zhong Li
Keyword(s):  
Image Retrieval ◽  
Feature Vector ◽  
Color Change ◽  
Color Space ◽  
Content Based Image Retrieval ◽  
Visual Feature ◽  
Image Content ◽  
Difference Statistic ◽  
Efficient Retrieval ◽  
Vector Clustering

Color is the most widely used visual feature in content based image retrieval. The visual coherence color space, HSV, is adopted to represent image. Hue component is used to denote color. Hue difference statistic is proposed to extract color change information as supplement to color feature. The image is divided into sub images equally. Color and change information is extracted in each region. After feature vector clustering and coding, image content can be expressed as vector codes. The text based analysis technology is used for image retrieval. Experiments show that the proposed method can realize efficient retrieval for unconstrained scene images.

Feature vector clustering molecular pairs in computer simulations

2019 ◽  
Vol 40 (29) ◽  
pp. 2539-2549 ◽  
Author(s):  
Han‐Wen Pei ◽  
Aatto Laaksonen
Keyword(s):  
Computer Simulations ◽  
Feature Vector ◽  
Vector Clustering

Video Summarization Using Feature Vector Clustering

2020 ◽  
Author(s):  
Yash Dhamecha ◽  
Swanand Gadekara ◽  
Sai Deshmukh ◽  
Yashodhara Haribhakta
Keyword(s):  
Feature Vector ◽  
Video Summarization ◽  
Vector Clustering
Sign in / Sign up

Export Citation Format

Share Document