Artificial Neural Network-Based Speech Recognition Using Dwt Analysis Applied On Isolated Words From Oriental Languages

Malaysian Journal of Computer Science

Zahid Halim¹  Ghulam Abbas¹  Bacha Rehmam¹  Tufail Muhammad¹ 

关键词: Speech recognition;    Artificialneural networks;    Discrete wavelet transform;    Feature extraction;   

DOI  :  

学科分类：社会科学、人文和艺术（综合）

来源: University of Malaya * Faculty of Computer Science and Information Technology

【 摘 要 】

Speech recognition is an emerging research area having its focus on human computer interactions (HCI) andexpert systems. Analyzing speech signals are often tricky for processing, due to the non-stationary nature ofaudio signals. The work in this paper presents a system for speaker independent speech recognition, which istested on isolated words from three oriental languages, i.e., Urdu,Persian, and Pashto. The proposed approachcombines discrete wavelet transform (DWT) and feed-forward artificial neural network (FFANN) for thepurpose of speech recognition. DWT is used for feature extraction and the FFANN is utilized for theclassification purpose. The task of isolated word recognition is accomplished with speech signal capturing,creating a code bank of speech samples, and then by applying pre-processing techniques.For classifying a wavesample, four layered FFANN model is used with resilient back-propagation (Rprop). The proposed systemyields high accuracy for two and five classes.For db-8 level-5 DWT filter 98.40%, 95.73%, and 95.20%accuracy rate is achieved with 10, 15, and 20 classes, respectively. Haar level-5 DWT filter shows 97.20%,94.40%, and 91% accuracy ratefor 10, 15, and 20 classes, respectively. The proposed system is also comparedwith a baseline method where it shows better performance. The proposed system can be utilized as acommunication interface to computing and mobile devices for low literacy regions.

【 授权许可】

Unknown