An iVector Extractor Using Pre-trained Neural Networks for Speaker Verification

	An iVector Extractor Using Pre-trained Neural Networks for Speaker Verification
	Shanshan, Zhang; Rong, Zheng; Bo, Xu
	2014
会议名称	International Symposium on Chinese Spoken Language Processing
会议录名称	International Symposium on Chinese Spoken Language Processing
会议日期	2014
会议地点	Singapore
摘要	;The iVector representation of speech utterances is currently widely used in speaker and language recognition tasks. In this paper, an iVector extractor using pre-trained neural networks is proposed for speaker verification. It can be viewed as an alternative to the classical total variability approach. In the proposed system, a neural network with bottleneck layer is trained with speaker labeled utterances, then we utilize the bottleneck features of the network to represent the input utterance. As a new iVector representation, it shows comparable performance with the state-of-the-art Total Variability Model (TVM) based iVector extraction system on NIST 2008 SRE. We further achieve a 10% reduction in equal error rates with combination of the proposed extraction system and the TVM system.
关键词	Ivector Extractor Bottleneck Feature Speaker Verification
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41218
专题	复杂系统认知与决策实验室_听觉模型与认知计算数字内容技术与服务研究中心
通讯作者	Shanshan, Zhang
推荐引用方式 GB/T 7714	Shanshan, Zhang,Rong, Zheng,Bo, Xu. An iVector Extractor Using Pre-trained Neural Networks for Speaker Verification[C],2014.