Noise Effect on Arabic Alphadigits in Automatic Speech Recognition.
Yousef Ajami Alotaibi, Khondaker A. Mamun, Ghulam Muhammad · IPCV · 2009
Abstract - Automatic Speech Recognition (ASR) in Arabic speech, particularly Saudi accented speech, is a less researched area. Some efforts to develop ASR on Saudi accented Arabic speech in clean environment have been studied in previous literature. These papers discuss the difficulties and problems in Arabic ASR up to some extent. In this paper, we analyze the effect of noise at different Signal to Noise Ratio (SNR) on Saudi accented Arabic alphadigits. The experimental result shows the accuracy of 85.01% in clean environment, and 82.45% and 60.55% accuracy in noisy condition at SNR 20 dB and 5 dB, respectively. The most confusing alphadigits are also discussed both in clean and noisy conditions. Index Terms —Saudi accented Arabic speech, alphadigits, ASR, HMM, noise. 1 Introduction Automatic speech recognition (ASR) is rich in many languages like English, Japanese, Spanish, German, Mandarin, etc. However, ASR in Arabic speech, particularly Saudi accented speech, is a less researched area. Some efforts to develop ASR on Arabic speech in clean environment have been reported in the literature [1][2]. These papers discuss the difficulties and problems in Arabic ASR up to some extent. In this paper, we analyze the effect of noise on Arabic alphadigits. In best of our knowledge, it is the first attempt towards developing a noise-robust Arabic speech recognition system. Table 1 shows the 29 alphabets and the 10 digits of Arabic language along with the way of how to pronounce them, type of syllable, and number of syllables in every spoken alphadigit. All Arabic syllables must contain at least one vowel. Also Arabic vowels cannot be initials and they can occur either between two consonants or be the final phoneme in a word.