Mel-lp Based Generalized Cepstral Analysis for Noisy Speech Recognition Using Hmm
نویسندگان
چکیده
This paper deals with LP based Mel-Generalized cepstrum which has been used as front-end for Hidden Markov Model (HMM) based speech recognition and it incorporates equal-loudness power law as well as auditory-like frequency resolution. To utilize the generalized cepstral representation, the model spectrum can be varied continuously from the all-pole spectrum to that represented by the cepstrum according to the value of γ. The performance of Mel-LP based generalized cepstral analysis has been evaluated on Aurora-2 database for HMM based speech recognition. The word accuracy for Mel-Generalized cepstral analysis is found to be 63.63% for test set A. On the contrary, the conventional Mel-LPC gives 59.05% word accuracy.
منابع مشابه
Speech Emotion Recognition Based on Power Normalized Cepstral Coefficients in Noisy Conditions
Automatic recognition of speech emotional states in noisy conditions has become an important research topic in the emotional speech recognition area, in recent years. This paper considers the recognition of emotional states via speech in real environments. For this task, we employ the power normalized cepstral coefficients (PNCC) in a speech emotion recognition system. We investigate its perfor...
متن کاملMel-generalized cepstral analysis - a unified approach to speech spectral estimation
The generalized cepstral analysis method is viewed as a unified approach to the cepstral method and the linear prediction method, in which the model spectrum varies continuously from all-pole to cepstral according to the value of a parameter γ. Since the human ear has high resolution at low frequencies, introducing similar characteristics to the model spectrum, we can represent speech spectrum ...
متن کاملPerformance Evaluation of Blind Equalization for Mel-LPC based Speech Recognition under Different Noisy Conditions
This study is aimed to develop a noise robust distributed speech recognizer (DSR) for real-world applications by employing Blind Equalization (BEQ) for robust feature extraction. The main focus of the work is to cope with different noisy environments in recognition phase. To realize this objective, Mel-LP based speech analysis has been used in speech coding on the linear frequency scale by appl...
متن کاملPerformance Evaluation of CMN for Mel-LPC based Speech Recognition in Different Noisy Environments
This study is intended to develop a noise robust distributed speech recognizer for real-world applications by employing Cepstral Mean Normalization (CMN) for robust feature extraction. The main focus of the work is to cope with different noisy environments. To realize this objective, Mel-LP based speech analysis has been used in speech coding on the linear frequency scale by applying a first-or...
متن کاملModified Mfcc Methods Based on Kl- Transform and Power Law for Robust Speech Recognition
This paper presents robust feature extraction techniques, called Mel Power Karhunen Loeve Transform Coefficients (MPKC), Mel Power Coefficients (MPC) for an isolated digit recognition. This hybrid method involves Stevens’ Power Law of Hearing and Karhunen Loeve(KL) Transform to improve noise robustness. We have evaluated the proposed methods on a Hidden Markov Model (HMM) based isolated digit r...
متن کامل