Voice Control Application

Speech is the siraplist way to pass information to the system by people, and also can make the demands for the level of the operator' s professional technologies reduced lowering. On the one hand, there must be speech communication existing between operator and robot controlling system to make robot have true intelligence. So, there is practicality and foreground to be engaged in the research on speech control.Firstly, on the base of the speech model, this paper analyses and compares the advantage and the disadvantage between the dynamic time wrapping (DTW) and hidden Markov model(HMM). Because we are to design a speech control system which is for special operator and the number of command is less than 50, and dynamic time wrapping can meet the require, we choose the dynamic time wrapping to be the algorithm for speech recognition. The idea of the algorithm is to use the dynamic programming to align and normalize the sequences of acoustic features. The process of speech recognition goes along as following: pre-emphasis, frame blocking, windowing, autocorrelation analysis, LPC analysis, LPC parameter conversion to cepstrum coefficients, parameter weighting, temporal cepstral derivative. Secondly, considering the cost, the mount of computation and the memory, the author decides that ADSP2181, AD1847, V29C51000B-45PI are processor, A/D, off-chip memory of the speech control system respectively and designs the corresponding interface. At last , the author uses C language to test the algorithm and analysis the results. The data used in the model are from the speech signal of microphone and computer audio card. Through a great deal of experiment, we can draw a conclusion that the algorithm of DTW is more feasible.