Voice Activity Detection in Noisy Environments Based on Double-Combined Fourier Transform and Line Fitting. (6th August 2014)

• Record Type: Journal Article
• Authors: Park, Jinsoo; Kim, Wooil; Han, David K.; Ko, Hanseok
• Other Names: Gorriz Saez Juan Manuel Academic Editor.
• Is Part Of: TheScientificWorldjournal. Volume 2014(2014)
• Publication Date: 2014-08-06
• Subjects: Science -- Periodicals; Technology -- Periodicals; Medicine -- Periodicals; 505
• DOI: 10.1155/2014/146040
• Languages: English
• ISSNs: 2356-6140

Abstract

Abstract : A new voice activity detector for noisy environments is proposed. In conventional algorithms, the endpoint of speech is found by applying an edge detection filter that finds the abrupt changing point in a feature domain. However, since the frame energy feature is unstable in noisy environments, it is difficult to accurately find the endpoint of speech. Therefore, a novel feature extraction algorithm based on the double-combined Fourier transform and envelope line fitting is proposed. It is combined with an edge detection filter for effective detection of endpoints. Effectiveness of the proposed algorithm is evaluated and compared to other VAD algorithms using two different databases, which are AURORA 2.0 database and SITEC database. Experimental results show that the proposed algorithm performs well under a variety of noisy conditions.