A NOVEL NOISE IMMUNE APPROACH TO SPEECH RECOGNITION
作者单位:Artificial Creatures LabComputer Engineering Depr.Sharif University of TechnologyTehranIran Artificial Creatures LabComputer Engineering Depr.Sharif University of TechnologyTehranIran Speech Processing LabComputer Engineering Dept.Sharif University of TechnologyTehranIran Artificial Creatures LabComputer Engineering Depr.Sharif University of TechnologyTehranIran Speech Processing LabComputer Engineering Dept.Sharif University of TechnologyTehranIran
会议名称:《第11届国际模糊系统协会世界大会》
会议日期:2005年
关 键 词:Fuzzy Modeling Speech Recognition Genetic Algorithms
摘 要:正 This paper presents a novel approach to speech recognition using fuzzy modeling which is specifically designed to ignore noise. The task begins with conversion of speech spectrogram into a linguistic fuzzy description based on arbitrary colors and lengths. While phonemes are also described using these fuzzy measures, and recognition is done by a normal fuzzy reasoning, a genetic algorithm optimizes phoneme definitions so that to classify samples into correct phonemes. The method is tested over a standard speech data base and the results are compared with a widely used speech recognition approach.