Gody, A., Shabaan, M., Saleh, A. (2016). Automatic Speech Segmentation Using Hybrid Wavelet Features and HMM. The Egyptian Journal of Language Engineering, 3(2), 1-13. doi: 10.21608/ejle.2016.60172
Amr M. Gody; Manal Shabaan; Amr Saleh. "Automatic Speech Segmentation Using Hybrid Wavelet Features and HMM". The Egyptian Journal of Language Engineering, 3, 2, 2016, 1-13. doi: 10.21608/ejle.2016.60172
Gody, A., Shabaan, M., Saleh, A. (2016). 'Automatic Speech Segmentation Using Hybrid Wavelet Features and HMM', The Egyptian Journal of Language Engineering, 3(2), pp. 1-13. doi: 10.21608/ejle.2016.60172
Gody, A., Shabaan, M., Saleh, A. Automatic Speech Segmentation Using Hybrid Wavelet Features and HMM. The Egyptian Journal of Language Engineering, 2016; 3(2): 1-13. doi: 10.21608/ejle.2016.60172
Automatic Speech Segmentation Using Hybrid Wavelet Features and HMM
1Electrical Engineering Department, Faculty of Engineering, Fayoum University
2Electrical Engineering Department, Faculty of Engineering, Fayoum University, Egypt
Abstract
In this research, a novel feature set is used to automatically segment speech signal. Automatic segmentation is very useful especially for large database. A hybrid features model is created from wavelet packet analysis and mel-scale is used to train Hidden Markov Model (HMM) for phone boundary detection. HMM is implemented using the Hidden Markov Model Toolkit (HTK).The database (Ked-TIMIT) is used for result verifications and Mel Frequency Cepstral Coefficients (MFCC) is used as reference for evaluating the results of the proposed Hybrid model. The results are categorized for vowels, consonants and short phones. Phone duration and start location are used as metrics to evaluate the system success rate. Success rate of 74% is achieved for consonant detection, 72% for vowel detection and 58% for short phone detection. Using the simple metric that relies only on boundary locations but ignoring duration, the achieved results are 92.5% for consonant detection, 90% for vowel detection and 77.5% for short phoneme detection. In addition to boundary detection the proposed hybrid model is utilized to compare newly developed features called Mel scale Best Tree Encoding (Mel-BTE ) to the mostly used popular features MFCC along with all experiments using the same database. The relative results for Mel-BTE with respect to MFCC are 94.77% for consonant detection, 87.5% for vowel detection and 93.33% for short phoneme detection.
View on SCiNiTO
Top