Ning Geng-xin, Wei Gang, Kong Xiang-zhu. Novel Model Compensation Based on Non-uniform Spectral Compression Features[J]. Journal of Electronics & Information Technology, 2007, 29(6): 1384-1388. doi: 10.3724/SP.J.1146.2005.01316
Citation:
Ning Geng-xin, Wei Gang, Kong Xiang-zhu. Novel Model Compensation Based on Non-uniform Spectral Compression Features[J]. Journal of Electronics & Information Technology, 2007, 29(6): 1384-1388. doi: 10.3724/SP.J.1146.2005.01316
Ning Geng-xin, Wei Gang, Kong Xiang-zhu. Novel Model Compensation Based on Non-uniform Spectral Compression Features[J]. Journal of Electronics & Information Technology, 2007, 29(6): 1384-1388. doi: 10.3724/SP.J.1146.2005.01316
Citation:
Ning Geng-xin, Wei Gang, Kong Xiang-zhu. Novel Model Compensation Based on Non-uniform Spectral Compression Features[J]. Journal of Electronics & Information Technology, 2007, 29(6): 1384-1388. doi: 10.3724/SP.J.1146.2005.01316
A novel model compensation method is proposed, which integrates the Vector Taylor Series (VTS) approach with a robust feature extraction technique called SNR-dependent Non-uniform Spectral Compression (SNSC). The SNSC method is a spectral operation of magnitude transformation which resembles the human intensity-to-loudness conversion process and de-emphasizes noisy bands. Based on this mismatch function, which models the effect of the noise onto the clean speech in the Log-spectral domain together with the SNSC, a new model compensation procedure is derived. By adopting this novel model compensation approach, significant improvement over the PMC and VTS method can be found in different additive noisy environments at the expense of slight increase in computational complexity.
罗宇, 杜利民. 基于单高斯模型集的汉语美子带特征重建算法. 电子学报, 2004, 32(10): 1654-1657. Luo Yu and Du Li-min. Single Gauss model set based MAP data imputation method for Mel-frequency filter-bank vectors of chinese speech. Acta Electronica Sinica, 2004, 32(10): 1654-1657.[2]Ding Pei and Cao Z G. An efficient robust ASR system based on the combination of speech enhancement and HMM adaptation. Chinese Journal of Electronics, 2002, 11(3): 422-425.[3]Acero A, Deng L, Kristjansson T, and Zhang J. HMM adaptation using vector Taylor series for noise speech recognition. in Proc. ICSLP2000, Beijing, China, Oct. 2000: 869-872.[4]Hung J W, Shen J L, and Lee L S. New approach for domain transformation and parameter combination for improved accuracy in parallel model combination (PMC) techniques[J].IEEE Trans. on Speech and Audio Processing.2001, 9(8):842-854[5]Gong Y. Speech recognition in noisy environments: Asurvey[J].Speech Communication.1995, 16(3):261-291[6]Chu K K and Leung S H. SNR-dependent non-uniform spectral compression for noisy speech recognition. In Proc. ICASSP04, Montreal, Canada, May 2004: 973-976.[7]Abramowitz M and Stegun I A. Handbook of Mathematical Functions with Formulas, Graphs, and Mathematical Tables. New York: Dover Publications Inc., 1972.