首页>
外国专利>
Self-learning speaker adaptation based on spectral bias source decomposition, using very short calibration speech
Self-learning speaker adaptation based on spectral bias source decomposition, using very short calibration speech
展开▼
机译:基于频谱偏置源分解的自学扬声器自适应,使用非常短的校准语音
展开▼
页面导航
摘要
著录项
相似文献
摘要
A speaker adaptation technique based on the separation of speech spectra variation sources is developed for improving speaker- independent continuous speech recognition. The variation sources include speaker acoustic characteristics, and contextual dependency of allophones. Statistical methods are formulated to normalize speech spectra based on speaker acoustic characteristics and then adapt mixture Gaussian density phone models based on speaker phonologic characteristics. Adaptation experiments using short calibration speech (5 sec./speaker) have shown substantial performance improvement over the baseline recognition system.
展开▼