Paper Title:
GMM with Modified Weight Applied into Audio Segment Classification
  Abstract

GMM with modified weight is proposed, and it is applied into the audio segment classification. Since GMM is training only by intra-class data, during classification, there may be some components in different GMM overlapping each other. That means the likelihoods of the overlap components are similar, which will induce the confusion during classification. To avoid this, the weight in GMM is modified according to the distance of components. For that component easily to confuse, the weight is deduced to decrease the effect of the component in whole result. Instead, for that component with well separability, the weight is enhanced. Based on the ratio of sub-band energy and the proposed model, an optimized likelihood is further put forward, in which the length of clip can be adjusted. From experiments, it can be drawn that GMM with modified weight has better performance than traditional GMM, and combined with optimized likelihood, the performance can be further enhanced.

  Info
Periodical
Key Engineering Materials (Volumes 467-469)
Edited by
Dehuai Zeng
Pages
692-697
DOI
10.4028/www.scientific.net/KEM.467-469.692
Citation
L. Zhang, Y. Zhao, X. Z. Xiang, "GMM with Modified Weight Applied into Audio Segment Classification", Key Engineering Materials, Vols. 467-469, pp. 692-697, 2011
Online since
February 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Jin Qing Liu, Qun Zhen Fan
Abstract:In this paper, the purpose is to find a method that can be more suited to facial expression change and also improve the recognition rate. The...
813
Authors: Jie Xu
Abstract:Determining the onset of acoustic emissions (AE) signal is very time consuming if the onset is picked manually, so it is important to read...
3807
  | Authors: Dan Yang, Bin Xu, Lin Lin Ye, Xu Wang
Chapter 2: Sensors and Signal/Image Processing
Abstract:Wavelet Neural Network (WNN) Is a Time-frequency Analysis Method, which Detects the Subtle Small Changes in the Signal Frequency Domain....
127
Authors: Li Min Guo, Jian Lin Hu
Chapter 17: Automatic Control Technology
Abstract:at present, texture image recognition mostly is identified by using an intelligent algorithm which is based on the feature extraction method...
2178
Authors: Jin Hui Lin, Ji Xiang Zhang
Chapter 4: Data, Image and Signal Processing
Abstract:Multimedia technology development and the implementation of the Internet technology leading to a large number of image information appear,...
595