Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Unsupervised Keyword Spotting using Bounded Generalized Gaussian Mixture Model with ICA

Abstract: 

In this paper, bounded generalized Gaussian mixture model (BGGMM) using independent component analysis (ICA) is proposed and applied to an existing unsupervised keyword spotting setting for the generation of posteriorgrams. The ICA mixture model is trained without any transcription information to generate the posteriorgrams which further labels the speech frames of the keyword example(s) and test data. For the detection of occurrence of a specific keyword in the test data, the posteriorgrams of one or more keyword examples are compared with the posteriorgrams of test utterances using the segmental dynamic time warping (DTW). A score fusion method is used to obtain the result of the keyword detection by ranking the distortion scores of all the test utterances. The TIMIT speech corpus is used for the evaluation of this unsupervised keyword spotting setting. The keyword detection results demonstrate the viability and effectiveness of the proposed algorithm in unsupervised keyword spotting framework.

up
0 users have voted:

Paper Details

Authors:
Nizar Bouguila
Submitted On:
23 February 2016 - 1:44pm
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Muhammad Azam
Document Year:
2015
Cite

Document Files

Unsupervised keyword Spotting_Slides_GlobalSIP_2015.pdf

(105)

Subscribe

[1] Nizar Bouguila, "Unsupervised Keyword Spotting using Bounded Generalized Gaussian Mixture Model with ICA", IEEE SigPort, 2015. [Online]. Available: http://sigport.org/448. Accessed: Dec. 14, 2019.
@article{448-15,
url = {http://sigport.org/448},
author = {Nizar Bouguila },
publisher = {IEEE SigPort},
title = {Unsupervised Keyword Spotting using Bounded Generalized Gaussian Mixture Model with ICA},
year = {2015} }
TY - EJOUR
T1 - Unsupervised Keyword Spotting using Bounded Generalized Gaussian Mixture Model with ICA
AU - Nizar Bouguila
PY - 2015
PB - IEEE SigPort
UR - http://sigport.org/448
ER -
Nizar Bouguila. (2015). Unsupervised Keyword Spotting using Bounded Generalized Gaussian Mixture Model with ICA. IEEE SigPort. http://sigport.org/448
Nizar Bouguila, 2015. Unsupervised Keyword Spotting using Bounded Generalized Gaussian Mixture Model with ICA. Available at: http://sigport.org/448.
Nizar Bouguila. (2015). "Unsupervised Keyword Spotting using Bounded Generalized Gaussian Mixture Model with ICA." Web.
1. Nizar Bouguila. Unsupervised Keyword Spotting using Bounded Generalized Gaussian Mixture Model with ICA [Internet]. IEEE SigPort; 2015. Available from : http://sigport.org/448