This paper introduces a speech recognition system of Mandarin continuous digits based on Sphinx. The acoustic model of this system is produced by SphinxTrain, and the language model is acquired from the Cmuclmtk statistical language model. In addition, this system makes use of PocketSphinx recognition engine as a decoder. According to the experiment, the correct rate of this system to a sentence of random length made by speaker-independent is up to 89.58%, and the word correct rate is 97.20%. Therefore, the performance of this system is fairly well.
展开▼