Automated Speech Recognition System (ASR)

摘要

This paper reports the results of the first phase of a research work for building a high performance, speaker-independent natural Arabic speech recognition system. This work aims at developing an Arabic broadcast news transcription system and a base system for further research. Several concurrent recent advances in Arabic language processing were crucial for the success of this stage, e.g automatic generation of Arabic diacritical marks, and rule-based phoneme dictionary. The developed Arabic speech recognition system is based on the Carnegie Mellon university Sphinx tools.