Exploiting principal component analysis in modulation spectrum enhancement for robust speech recognition

Kun Shan University Institutional Repository > 教學單位 > 工程學院 > 環境工程系所 > 期刊論文 > Item 987654321/17447

Please use this identifier to cite or link to this item: http://ir.lib.ksu.edu.tw/handle/987654321/17447

Title:	Exploiting principal component analysis in modulation spectrum enhancement for robust speech recognition
Authors:	李詹儀
Keywords:	robust speech recognition;modulation spectrum;principal component analysis
Date:	2011-07
Issue Date:	2012-09-10 14:31:10 (UTC+8)
Abstract:	In this paper, we present a novel method to improve the noise robustness of speech features based on principal component analysis (PCA). The PCA process is employed to extract a set of basis spectral vectors for the modulation spectra of clean training speech features. The new modulation spectra of the speech features, constructed by mapping the original modulation spectra into the space spanned by these PCA-derived basis vectors, have shown robustness against the noise distortion. The experiments conducted on the Aurora-2 digit string database revealed that the proposed PCAbased approach, together with mean and variance normalization (MVN), can provide average error reduction rates of over 65% and 12% relative as compared with the baseline MFCC system and that using the MVN method alone, respectively.
Appears in Collections:	[環境工程系所] 期刊論文

Files in This Item:

File	Description	Size	Format
李詹儀-成果呈現.pdf		336Kb	Adobe PDF	587	View/Open

View Licence