Evaluation of Phonetic System for Speech Recognition on Smartphone
Gulbakshee J Dharmale1, Dipti D Patil2
1Gulbakshee J. Dharmale, Department of Computer Science and Engineering, Sant Gadge Baba Amravati University, Amravati, India
2Dipti D. Patil, Department of Information Technology, MKSSS’s Cummins College of Engineering for Women, Pune, India.
Manuscript received on 09 August 2019 | Revised Manuscript received on 17 August 2019 | Manuscript published on 30 August 2019 | PP: 3354-3359 | Volume-8 Issue-10, August 2019 | Retrieval Number: J12150881019 /19©BEIESP | DOI: 10.35940/ijitee.J1215.0881019
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper presents detailed study and performance evaluation of phonetic system by comparing it with various classification techniques of automatic speech recognition such as Neural Network, Hidden Markov Model, Support Vector Machine and Gaussian Mixture Model. In the phonetic system, recognized speech is processed by using language processing i.e. matching phonemes and hence generates more correct output text. The accuracy of speech recognition of ASR classifier and phonetic system is evaluated on day to day human to machine communications, using high-quality recording equipment, while the results for enhancement of existing systems is done on everyday android phones, and evaluated for normal conversations in Hindi and English language. Classifier is used to classify the fragmented phonemes or words after the fragmentation of the speech signal. Different classification techniques are implemented and comparing accuracy of speech recognition of different classifier. It is seen that GMM is better at the classification of signal data, outcomes of performance evaluation shows that GMM outperforms the other three classifiers in terms of accuracy by more than 20%. This result is compared with implemented phonetic system which shows that ASR accuracy, using phonetic system is better than GMM. We observed 6% improvement in ASR accuracy with phonetic system.
Keywords: Automatic Speech Recognition (ASR), Mel Frequency Cepstral Coefficient (MFCC), Gaussian Mixture Model (GMM), Speech Enhancement, Hidden Markov Model (HMM)
Scope of the Article: Pattern Recognition