Investigating Morphological Decomposition for Transcription of Arabic Broadcast News and Broadcast Conversation Data

摘要

One of the challenges of Arabic speech recognition is to deal with the huge lexical variety. Morphological de-composition has been proposed to address this problem by increasing lexical coverage, thereby reducing errors that are due to words that are unknown to the system. In our previous attempts to develop an Arabic speech-to-text (STT) transcription system with morphological decom-position, an increase in word error rate of about 2% ab-solute was observed relative to a comparable word based system. Based on an error analysis and a comparison of our approach with that of other sites, two modifications were made. The first modification was to not decompose the most frequent words; and the second to not decom-pose the prefix 'Al' for words starting with a solar con-sonant since due to assimilation with the following con-sonant, deletion of the prefix was one of the most fre-quent errors. Comparable recognition performance was achieved using word-based and morphologically decom-posed language models, and since the errors made by the systems are different, combining the two gave a perfor-mance gain.