Researching And Building Of The Mongolian Continuous Speech Recognition System Based On HMM

To make computer hearing is the object of speech recognition, namely make the computer exactly recognize the content of speech under various conditions, and can implement the intention of people according to the speech. Speech recognition is a cross-subject relating to many aspects, which has close relationship with computer science, communications, linguistics, signal processing and artificial intelligence. This thesis is a project between College of Computer Scince Inner Mogolia University and Institute of Automation Chinese Academy of Sciences, which is named " Researching of the Mongolian Continuous Speech Recognition".Mongolian is belonged to Altai phylum, and similar with language of the West. According to the characteristics of Mongolian pronunciation, we build the Mongolian acoustic model. We collected a large size corpus to construct the language model.The Mongolian large vocabulary speech recognition system uses HTK as training and recognition toolkit, uses tri-phone models as basic recognition sub-word units, and statistical language model was used for the experiment.This paper consists of seven parts. The first one clarifies the significance of speech recognition research, and then introduces the history and actuality of Mongolian speech recognition. Finally it introduces primary contents of this paper and the results of them. The second part is a system with speech recognition. It introduces speech signal processing. The third part is a brief introduction on the theory of Hidden Markov Model (HMM). In Chapter four, it introduces establishment of speech corpus and recording of a Mongolain speech recognition system basing on HMM. In Chapter five, I introduce a Mongolian speech recognition system basing on HMM. In Chapter six, the thesis shows several recognition experiments based on the upper research. Future work is narrated at the end of this thesis.