Information Retrieval Method of Professional Music Teaching Based on Hidden Markov Model

To facilitate professional users to find multimedia files composed of music information more quickly and realize audio frequency content information retrieval, this paper proposes a solution of automatic classification using HMM. Considering the traditional timbre features, the preprocessing process of speech signal is analyzed, and the common feature parameter extraction methods are compared to denoise audio information from the aspects of structure and state number. Then HMM model based on notes is used for training and recognition to realize the feature extraction of teaching audio/video files. The simulation results show that the audio classification performance of the hidden Markov model proposed in this paper has better performance, and the optimal classification accuracy is more than 90%.