An approach of agricultural price information collection based on speech recognition

Speech recognition technology was applied to information collection of agricultural prices, with the acoustic models trained for agricultural prices information collection environment so as to minimize the environmental influence. Firstly, we constructed the speech corpus by collecting speech under the operating scene, and then selected tri-phone modeling as the decode unit to train hidden Markov model (HMM) for the recognition of male and female voices. Secondly, decision tree-based clustering of states was used to solve the problem caused by insufficiency in training samples, and then increased mixture of Gaussian components to make the model more accurately described. In the end, we adopted the CMN and CVN methods (often used in conjunction, called CMVN) to reduce the mismatch between testing and the training environment. From the test results of different locations and different speakers, the ultimate recognition rate reached 95.04% for males, and 97.62% for females.