期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2019
卷号：97
期号：14
页码：3990-3999
出版社：Journal of Theoretical and Applied
摘要：Automatic Speech Recognition (ASR) is a technology by which a computer can distinguish the words that a person talks into a microphone or a telephone. It is a key technology for many applications. It is gaining a growing role in a variety of application such as telephone communication with information systems, automatic query answering, hands free operation control as in airplanes and car, speech-to-text transcription, etc. ASR can help also, handicapped people to interact with society. Due to the ASR importance many systems are developed, the most common are: Dragon Naturally Speaking, IBM via voice, Microsoft SAPI. Also, many speech recognizing open source systems are available too. One of the main obstacles challenge the development of ASR applications for Arabic speech is the rarity of suitable sound databases commonly required for training and testing statistical models. The pronunciation (or phonetic) dictionary is an important ASR component that serves as an intermediate between language models and acoustic models in ASR systems. It holds a subset of the words available in the language and the pronunciation variants of each word in terms of sequences of the phonemes existing in the acoustic models. The development of perfect Automatic Arabic Speech Recognition (ASR) systems is challenged with the accuracy of the phonetic dictionary.
