Mean normalization of power function based cepstral coefficients for robust speech recognition in noisy environment

International Conference
2014-05-01 00:42
Authors : Soonho Baek, Hong-Goo Kang

Year : 2014

Publisher / Conference : ICASSP

This paper presents the effect of mean normalization to various types of cepstral coefficients for robust speech recognition in noisy environments. Although the cepstral mean normalization (CMN) technique was originally designed to compensate channel distortion, it has also been proved that the CMN also improves recognition accuracy in additive noisy environment. However, no one has yet considered the interaction of CMN with spectral mapping functions required for extracting cepstral features. This paper investigates the impact of CMN to the speech recognition system depending on the types of spectral mapping function by mathematically analyzing the amount of spectral distortion between clean and noisy conditions. The analytic result is also confirmed by comparing the type of recognition error patterns in automatic speech recognition experiment with Aurora 2 database. Experimental results show that the performance improvement by adopting CMN becomes significant if the logarithmic function is replaced with the appropriate setting of fractional power mapping function. Especially, the deletion errors are dramatically reduced.
전체 326
71 International Conference Soonho Baek, Hong-Goo Kang "Mean normalization of power function based cepstral coefficients for robust speech recognition in noisy environment" in ICASSP, 2014
70 International Conference Ho Seon Shin, Hong-Goo Kang "Bone-Conduction Speech Enhancement using a Speaker-Independent Filter" in ICEIC, 2014
69 International Conference Soonho Baek, Hong-Goo Kang "Vector Taylor Series based HMM Adaptation for Generalized Cepstrum in Noisy Environment" in ASRU, 2013
68 International Conference Jung-Won Lee, Hong-Goo Kang, Samuel Kim, Yoonjae Lee "Detecting pathological speech using local and global characteristics of harmonic-to-noise ratio" in APSIPA, 2013
67 International Conference Eunwoo Song, Jongyoub Ryu, Hong-Goo Kang "Speech enhancement for pathological voice using time-frequency trajectory excitation modeling" in APSIPA, 2013
66 International Conference Jinkyu Lee, Hyunson Seo, Hong-Goo Kang "Adaptation of HMM dynamic parameters in reverberant environment" in EUSIPCO, 2013
65 International Conference Jae-Mo Yang, Hong-Goo Kang "Adaptive multichannel linear prediction based dereverberation in time-varying room environments" in EUSIPCO, 2013
64 International Conference JeeSok Lee, Frank Soong, Hong-Goo Kang "Source-Filter based Full-band Adaptive Harmonic Model and Its Application to Speech Prosody Modification" in INTERSPEECH, 2013
63 International Conference Young-Sun Joo, Chi-Sang Jung, Hong-Goo Kang "Enhancement of spectral clarity for HMM-based text-to-speech systems" in ICASSP, 2013
62 International Conference Taegyu Lee, Seokjin Lee, Young-cheol Park, Dae Hee Youn "Virtual bass system based on a multiband harmonic generation" in ICCE, 2013