摘要
Based on the spectrograms analysis and the individual frequency bands of speech under G-force, in this pa-per, a new Mel frequency scale is proposed, and the related MFCC (Mel Frequency Cepstrum Coefficient) is adoptedas the features for recognition of stressed speech under G-force. It is shown from the experiments that the proposedmethod is better than other methods of Mel-based features for stressed speech recognition.
Based on the spectrograms analysis and the individual frequency bands of speech under G-force, in this paper, a new Mel frequency scale is proposed, and the related MFCC (Mel Frequency Cepstrum Coefficient) is adopted as the features for recognition of stressed speech under G-force. It is shown from the experiments that the proposed method is better than other methods of Mel-based features for stressed speech recognition.
出处
《计算机科学》
CSCD
北大核心
2002年第12期150-153,共4页
Computer Science
基金
国家自然科学基金(项目批准号:60085001)
教育部留学回国人员科研启动基金
关键词
变异语音识别
语音参数
Mel频率映射
语音信号处理
Stressed speech recognition, G-force, Mel frequency. Mel frequency cepstrum coefficient
