学位论文详细信息
Multiview feature learning for speech recognition
Multiview learning;canonical correlation analysis;articulatory measurements;dimensionality reduction;acoustic features
Bharadwaj, Sujeeth ; Hasegawa-Johnson ; Mark A.
关键词: Multiview learning;    canonical correlation analysis;    articulatory measurements;    dimensionality reduction;    acoustic features;   
Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/29785/Bharadwaj_Sujeeth.pdf?sequence=1&isAllowed=y
美国|英语
来源: The Illinois Digital Environment for Access to Learning and Scholarship
PDF
【 摘 要 】

In this thesis, we study the problem of learning a linear transformation of acoustic feature vectors for speech recognition, in a framework where apart from the acoustics, additional views are available at training time.We consider a multiview learning approach based on canonical correlation analysis to learn linear transformations of the acoustic features that are maximally correlated with the data.We propose simple approaches for combining information shared across the views with information that is private to the acoustic view.We apply these methods to a specific scenario in which articulatory data is available at training time.Results of phonetic frame classification on data drawn from the University of Wisconsin X-ray Microbeam Database indicate a small but consistent advantage to the multiview approaches that combine shared and private information, compared to the baseline acoustic features or unsupervised dimensionality reduction using principal component analysis.We then discuss limitations of canonical correlation analysis and possible extensions.

【 预 览 】
附件列表
Files Size Format View
Multiview feature learning for speech recognition 587KB PDF download
  文献评价指标  
  下载次数:14次 浏览次数:14次