scholarly journals Continuous Speech Recognition System for Kannada Language with Triphone Modelling using HTK

2019 ◽  
Vol 8 (3) ◽  
pp. 7827-7831
Keyword(s):  
Speech Recognition ◽  
Recognition Accuracy ◽  
Gaussian Mixture ◽  
Recognition System ◽  
Experimental Result ◽  
Speech Recognition System ◽  
Continuous Speech Recognition ◽  
Frequency Scale ◽  
Context Dependent ◽  
Mel Frequency Cepstral Coefficient

Kannada is the regional language of India spoken in Karnataka. This paper presents development of continuous kannada speech recognition system using monophone modelling and triphone modelling using HTK. Mel Frequency Cepstral Coefficient (MFCC) is used as feature extractor, exploits cepstral and perceptual frequency scale leads good recognition accuracy. Hidden Markov Model is used as classifier. In this paper Gaussian mixture splitting is done that captures the variations of the phones. The paper presents performance of continuous Kannada Automatic Speech Recognition (ASR) system with respect to 2, 4,8,16 and 32 Gaussian mixtures with monophone and context dependent tri-phone modelling. The experimental result shows that good recognition accuracy is achieved for context dependent tri-phone modelling than monophone modelling as the number Gaussian mixture is increased.

scholarly journals Developing Speech Recognition System for Quranic Verse Recitation Learning Software

2012 ◽  
Vol 1 (2) ◽  
pp. 14
Author(s):  
Budiman Putra ◽  
B. Atmaja ◽  
D. Prananto
Keyword(s):  
Speech Recognition ◽  
Learning Process ◽  
Gaussian Mixture ◽  
Recognition System ◽  
Speech Recognition System ◽  
Multimedia Software ◽  
Experiment Data ◽  
Learning Flexibility ◽  
Learning Software ◽  
Mel Frequency Cepstral Coefficient

Quran as holy book for Muslim consists of many rules which are needed to be considered in reading Quran verse properly. If the recitation does not meet all of those rules, the meaning of Quran verse recited will be different with its origins. Intensive learning is needed to be able to do correct recitation. However, the limitation of teachers and time to study Quran verse recitation together in a class could be an obstacle in Quran recitation learning. In order to minimize the obstacle and to ease the learning process we implement speech recognition techniques based on Mel Frequency Cepstral Coefficient (MFCC) features and Gaussian Mixture Model (GMM) modeling, we have successfully designed and developed Quran verse recitation learning software in prototype stage. This software is interactive multimedia software which has many features for learning flexibility and effectiveness. This paper explains the developing of speech recognition system for Quran learning software which is built with the ability to perform evaluation and correction in Quran recitation. In this paper, the authors present clearly the built and tested prototype of the system based on experiment data.

Keyword Recognition Based on MFCC

2014 ◽  
Vol 926-930 ◽  
pp. 1729-1732
Author(s):  
Sha Yang ◽  
Tian Hu ◽  
Yun Lu Zhang
Keyword(s):  
Speech Recognition ◽  
Recognition Accuracy ◽  
Hidden Markov ◽  
Recognition System ◽  
Recognition Algorithm ◽  
Speech Recognition System ◽  
Continuous Speech Recognition ◽  
Recognition Time ◽  
State 1 ◽  
Model Approach

After about 50 years of development, speech recognition technology has been able to achieve large vocabulary, non-specific human continuous speech recognition system. On account of Chinese pronunciation features, we research the small vocabulary, non-specific Chinese speech recognition based on continuous Hidden Markov Model approach. With comparing the datasets of VQ/DTW, VQ/DHMM, CHMM state-1 recognition algorithm and CHMM state-2 recognition algorithm, the results of our experiment show that: (1) CHMM state-2 branch method performs primely in reduction of the recognition time; and (2) the recognition accuracy is improved eventually.

Sign in / Sign up

Export Citation Format

Share Document