Noise Adaptive Training For Subspace Gaussian Mixture Models
14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5(2013)
摘要
Noise adaptive training (NAT) is an effective approach to normalise environmental distortions when training a speech recogniser on noise-corrupted speech. This paper investigates the model-based NAT scheme using joint uncertainty decoding (JUD) for subspace Gaussian mixture models (SGMMs). A typical SGMM acoustic model has much larger number of surface Gaussian components, which makes it computationally infeasible to compensate each Gaussian explicitly. JUD tackles this problem by sharing the compensation parameters among the Gaussians and hence reduces the computational and memory demands. For noise adaptive training, JUD is reformulated into a generative model, which leads to an efficient expectation-maximisation (EM) based algorithm to update the SGMM acoustic model parameters. We evaluated the SGMMs with NAT on the Aurora 4 database, and obtained higher recognition accuracy compared to systems without adaptive training.
更多查看译文
关键词
adaptive training,noise robustness,joint uncertainty decoding,subspace Gaussian mixture models
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络