JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/11513

Title: Comparative investigation of objective speech intelligibility prediction measures for noise-reduced signals in Mandarin and Japanese
Authors: Li, Junfeng
Chen, Fei
Akagi, Masato
Yan, Yonghong
Keywords: Speech intelligibility
objective intelligibility prediction
noise reduction
Issue Date: 2013-08-27
Publisher: International Speech Communication Association
Magazine name: Proceedings of InterSpeech 2013
Start page: 1184
End page: 1187
Abstract: In this paper, eight state-of-the-art objective speech intelligibility prediction measures are comparatively investigated for noisy signals before and after noise-reduction processing between Mandarin and Japanese. Clean speech signals (Chinese words and Japanese words) were first corrupted by three types of noise at two signal-to-noise ratios and then processed by normal-hearing listeners for recognition, whose intelligibility was subsequently predicted by objective measures. Further investigations were conducted for objective measures in predicting speech intelligibility of noise-reduced signals between subjective evaluation scores and objective prediction results, and of noisy signals before and after noise-reduction processing, in terms of correlation analysis and prediction errors. Results showed that the majority of objective measures behave differently for Mandarin and Japanese in predicting the subjective ratings, and the STOI measure consistently provided the best ability in predicting the effect on speech intelligibility of the noise-reduction processing for both Mandarin and Japanese.
Rights: Copyright (C) 2013 International Speech Communication Association. Junfeng Li, Fei Chen, Masato Akagi, Yonghong Yan, Proceedings of InterSpeech 2013, 2013, pp.1184-1187.
URI: http://hdl.handle.net/10119/11513
Material Type: publisher
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
IS2013_Li.pdf186KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.

 


Contact : Library Information Section, Japan Advanced Institute of Science and Technology