Recent improvements to the Cambridge Arabic Speech-to-Text systems
Marcus Tomalin, Frank Diehl, Mark Gales, J. Park, Philip C. Woodland · 2010
This paper describes recent improvements to the Cambridge Arabic Large Vocabulary Continuous Speech Recognition (LVSCR) Speech-to-Text (STT) system. It is shown that Multi-Layer Perceptron (MLP) features trained on phonetic targets can improve the performance of both phonemic and graphemic systems. Also, a morphological decomposition scheme is extended from the graphemic domain to the phonetic domain, and particular attention is given to the task of dictionary generation. Finally, the use of Boosted Maximum Mutual Information (BMMI) training is explored both for individual systems and in the context of system combination. The full system results show that the combined use of the above techniques reduces the Word Error Rate (WER) of the best individual system by up to 12% relative, and that the incorporation of morphological decomposition and BMMI within the four individual branches of the combined system reduces the WER by up to 9% relative.