首页>
外国专利>
Method for additive and convolutional noise adaptation in automatic speech recognition using transformed matrices
Method for additive and convolutional noise adaptation in automatic speech recognition using transformed matrices
展开▼
机译:利用变换矩阵的自动语音识别中的加性和卷积噪声自适应方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
A noise adaptation system and method provide for noise adaptation in a speech recognition system. The method includes the steps of generating a reference model based on a training speech signal, and compensating the reference model for additive noise in the cepstral domain. The reference model is also compensated for convolutional noise in the cepstral domain. In one embodiment, the convolutional noise is compensated for by estimating a convolutional bias between the reference model and a target speech signal. The estimated convolutional bias is transformed with a channel adaptation matrix, and the transformed convolutional bias is added to the reference model in the cepstral domain.
展开▼