首页>
外国专利>
Training wideband acoustic models in the cepstral domain using mixed-bandwidth training data and extended vectors for speech recognition
Training wideband acoustic models in the cepstral domain using mixed-bandwidth training data and extended vectors for speech recognition
展开▼
机译:使用混合带宽训练数据和用于语音识别的扩展矢量在倒频谱域中训练宽带声学模型
展开▼
页面导航
摘要
著录项
相似文献
摘要
A method and apparatus are provided that generate values for a first set of dimensions of a feature vector from a speech signal. The values of the first set of dimensions are used to estimate values for a second set of dimensions of the feature vector to form an extended feature vector. The extended feature vector is then used to train an acoustic model.
展开▼