Two-Stage Multi-Target Joint Learning for Monaural Speech Separation

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 机器人视觉团队

	Two-Stage Multi-Target Joint Learning for Monaural Speech Separation
	Shuai, Nie 1; Shan, Liang1 ; Wei, Xue 1; XueLiang, Zhang 2; WenJu, Liu1 ; Like Dong 3; Hong Yang 3
	2015
会议名称	Annual Conference of the International Speech Communication Association (INTERSPEECH)
会议日期	2015
会议地点	Dresden Germany
关键词	speech separation multi-target learning computational auditory scene analysis (CASA)
页码	1503-1507
英文摘要	Recently, supervised speech separation has been extensively studied and shown considerable promise. Due to the temporal continuity of speech, speech auditory features and separation targets present prominent spectro-temporal structures and strong correlations over the time-frequency (T-F) domain, which can be exploited for speech separation. However, many supervised speech separation methods independently model each T-F unit with only one target and much ignore these useful information. In this paper, we propose a two-stage multi-target joint learning method to jointly model the related speech separation targets at the frame level. Systematic experiments show that the proposed approach consistently achieves better separation and generalization performances in the low signal-to-noise ratio(SNR) conditions.
收录类别	EI
会议录	Annual Conference of the International Speech Communication Association (INTERSPEECH)
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/11024]
专题	自动化研究所_模式识别国家重点实验室_机器人视觉团队
作者单位	1.National Laboratory of Patten Recognition, Institute of Automation, Chinese Academy of Sciences 2.College of Computer Science, Inner Mongolia University 3.Electric Power Research Institute of ShanXi Electric Power Company, China State Grid Corp
推荐引用方式 GB/T 7714	Shuai, Nie,Shan, Liang,Wei, Xue,et al. Two-Stage Multi-Target Joint Learning for Monaural Speech Separation[C]. 见:Annual Conference of the International Speech Communication Association (INTERSPEECH). Dresden Germany. 2015.