A Front-End Processing Using Subspace-Based Speech Enhancement Over Mobile Devices

The paradigm multi-stream has been shown to result in features combined that can help to increase the robustness of Distributed Speech Recognition (DSR) in the mobile communications. In this paper, the author's employs a combination of post proceeded Mel-Frequency Cepstral Coefficients (MFCCs) and Line Spectral Frequencies (LSFs) features projected in Linear Discriminate Analysis (LDA) space. The experiments performed on the Aurora 2.0 database using multi-condition training set show that, even with fewer parameters, the proposed front-end provides comparable recognition results to the standard ETSI WI008 advanced front-end, now-a-days available in the vocal commands of the GSM mobile communications, while achieving higher accuracy when the Signal-to-Noise Ratio (SNR) is very low.

Provided by: International Association of Computer Science and Information Technology(IACSIT) Topic: Mobility Date Added: Mar 2014 Format: PDF

Find By Topic