QQ客服 官方微博 反馈留言

	Language identification based on auditory features
	Zhang Weiqiang ; Liu Jia
	2010-10-12 ; 2010-10-12
关键词	Practical/ channel bank filters feature extraction hearing natural languages speech recognition/ language identification auditory-based feature extraction algorithm Gammatone filter bank triangle filter bank subband energy equivalent rectangular bandwidth model subjective human loudness perception frequency component inverse equal loudness curve first-order delta cepstrum second-order delta cepstrum shifted delta cepstrum Mel-frequency cepstrum coefficient MFCC speech recognition/ B6130E Speech recognition and synthesis B6140B Filtering methods in signal processing C5260S Speech processing techniques C6180N Natural language processing
中文摘要	An auditory-based feature extraction algorithm was developed to improve the recognition performance of language identification algorithms using human auditory characteristics. The sub-band energies of the extracted auditory features were calculated using a Gammatone filter bank instead of the commonly used triangle filter bank. The center frequencies and bandwidths were then determined according to the equivalent rectangular bandwidth (ERB) model. The subjective human loudness perception for different frequency components was simulated by an inverse equal loudness curve. The first- and second-order delta cepstrum and the shifted delta cepstrum were derived based on these auditory features. Tests show that the features outperform the widely used Mel-frequency cepstrum coefficient (MFCC) counterparts.
语种	中文
出版者	Tsinghua University Press ; China
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/82603]
专题	清华大学
推荐引用方式 GB/T 7714	Zhang Weiqiang,Liu Jia. Language identification based on auditory features[J],2010, 2010.
APA	Zhang Weiqiang,&Liu Jia.(2010).Language identification based on auditory features..
MLA	Zhang Weiqiang,et al."Language identification based on auditory features".(2010).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。