DSpace Repository

Theoretical Analysis of Parametric Blind Spatial Subtraction Array and Its Application to Speech Recognition Performance Prediction

Show simple item record

dc.contributor.author Ryoichi Miyazaki en
dc.contributor.author Hiroshi Saruwatari en
dc.contributor.author Ryo Wakisaka en
dc.contributor.author Kiyohiro Shikano en
dc.contributor.author Tomoya Takatani en
dc.date.accessioned 2013-11-20T02:30:32Z en
dc.date.available 2013-11-20T02:30:32Z en
dc.date.issued 2011 en
dc.identifier.isbn 9781457709975 en
dc.identifier.uri http://hdl.handle.net/10061/9206 en
dc.description HSCMA 2011: The Third Joint Workshop on Hands-free Speech Communication and Microphone Arrays, 30 May - 1 June, 2011, Edinburgh, UK. en
dc.description.abstract In this paper, an improved parametric postfiltering is introduced in our previously proposed blind spatial subtraction array (BSSA), and its theoretical analysis of the amounts of musical noise and noise reduction is conducted via higher-order statistics. Compared with the conventional BSSA, it is clarified that parametric BSSA can improve speech recognition performance. Next, we propose an unsupervised speech-recognition-performance prediction metric based on higher-order statistics in BSSA. We successfully reveal that the noise and speech kurtosis can be used for predicting speech recognition performance without using any reference speech signals. en
dc.language.iso en en
dc.publisher IEEE en
dc.rights Copyright c 2011 IEEE en
dc.title Theoretical Analysis of Parametric Blind Spatial Subtraction Array and Its Application to Speech Recognition Performance Prediction en
dc.type.nii Conference Paper en
dc.textversion Publisher en
dc.identifier.spage 19 en
dc.identifier.epage 24 en
dc.relation.doi 10.1109/HSCMA.2011.5942397 en


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account