Multilingual Tandem Bottleneck Feature For Language Identification

	Multilingual Tandem Bottleneck Feature For Language Identification
	Wang Geng; Jie Li,; Shanshan Zhang; Xinyuan Cai; Bo Xu; Xinyuan.Cai
	2016-09
会议名称	Interspeech 2015
会议录名称	Interspeech2015
会议日期	2016.9.6-2016.9.10
会议地点	Dresden,German
摘要	The deep bottleneck (BN) feature based ivector solution has been recognized as a popular pipeline for language identification (LID) recently. However, issues such as how to extract more effective BN features and how to fully utilize features extracted from deep neural networks (DNN) are still not well investigated. In this paper, these issues are empirically tackled by means as follows: First, two novel types of deep features, phone-discriminant and triphone-discriminate are extracted. Then, DNNs are trained both separately and jointly on multilingual corpuses to produce different BN features. Finally, tandem fashion on deep BN features is applied to build enhanced deep features. Experiment results show that systems built on top of tandem deep features obtain 19% and 42% relative equal error rate reduction on average on NIST LRE 2007 over the counterpart built on traditional deep BN features and the cepstral feature based LID system, respectively
关键词	Language Identification Deep Bottleneck Feature Tandem Feature Multi-deep Feature Multi-training Procedure.
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41095
专题	复杂系统认知与决策实验室_听觉模型与认知计算
通讯作者	Xinyuan.Cai
推荐引用方式 GB/T 7714	Wang Geng,Jie Li,,Shanshan Zhang,et al. Multilingual Tandem Bottleneck Feature For Language Identification[C],2016.