Recognition of Arabic speech sound error in children
- PDF / 791,888 Bytes
- 7 Pages / 595.276 x 790.866 pts Page_size
- 98 Downloads / 245 Views
Recognition of Arabic speech sound error in children Nacereddine Hammami1 · Isah A. Lawal2 · Mouldi Bedda3 · Nadir Farah4 Received: 1 July 2019 / Accepted: 12 August 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The accurate and automatic recognition of speech sound errors in children is crucial to facilitate the early detection and correction of any faulty phonological process in their early life. This paper addresses the problem of speech sound error classification in native Arabic children when they wrongly pronounce Arabic words containing the letter r (pronounced as /ra/). We identify whether the speech sound error occurs when the letter appears at the beginning, middle, or end of the words. To classify the spoken words, we represent the speech signal with Mel Frequency Cepstral Coefficients (MFCC) features and then train a probabilistic classifier. We evaluate the performance of our proposed approach using a real-world database consisting of speech recordings from native Arabic speaking children. The proposed method achieves a classification accuracy of 71.75%, 77.20%, and 74.06% on average, for speech sound error with Arabic words containing the letter r at the beginning, middle, and end of the words, respectively. These results are superior to those obtained with Hidden Markov Model: another state-of-the-art method on the same dataset. Keywords Speech sound error · Arabic speech classification · Probabilistic classifier · Gaussian copula
1 Introduction Speech is the primary means of verbal communication between people. However, some people are unable to verbally communicate effectively because of speech sound disorder (Bader 2009; Gad-Allah et al. 2012). Speech Sound Disorder (SSD) occurs when a person has difficulties pronouncing certain sounds and words (El-Gayyar et al. 2016). * Isah A. Lawal [email protected] Nacereddine Hammami [email protected] Mouldi Bedda [email protected] Nadir Farah [email protected] 1
Department of Computer and Network Engineering, Jouf University, Sakaka, Saudi Arabia
2
Faculty of Applied Computing and Technology (FACT), Noroff University College, Kristiansand, Norway
3
Department of Electrical Engineering, Jouf University, Sakaka, Saudi Arabia
4
Department of Mathematics‑Computer Science, Badji Mokhtar University, Annaba, Algeria
This speech impairment makes it hard to understand what the person is trying to say. With children of 5 years and above, the possibility of SSD is high when they continue to have difficulties pronouncing some sounds or words.1 There are two types of SSD: articulation disorder and phonological process disorder. A child with articulation disorder cannot pronounce some words, however, a child with phonological process disorder continues to make a pattern of sound errors, including distortion, omission, and addition.2 With distortion, a child may pronounce a word by producing an erroneous sound of one or more of the letters. At times, the sound of a letter is replaced with the sound of another on
Data Loading...
