On Reliability of Log-Spectral Distortion Measure in Speech Quality Estimation

被引：0

作者：

Prodeus, Arkadiy ^{[1
]}

Kotvytskyi, Igor ^{[1
]}

机构：

[1] NTUU Igor Sikorsky KPI, Fac Elect, Acoust & Acoustoelect Dept, Kiev, Ukraine

来源：

2017 IEEE 4TH INTERNATIONAL CONFERENCE ACTUAL PROBLEMS OF UNMANNED AERIAL VEHICLES DEVELOPMENTS (APUAVD) | 2017年

关键词：

speech quality; log-spectral distortion; speech signals limited in the frequency band; signal model; signal spectrum;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, the results of experimental studies of the reasons for the low reliability of the log-spectral distortion (LSD) measure for estimating the quality of speech signals limited in the frequency band are presented. It is shown that the LSD measure has an increased sensitivity not only to the speech formants, but also to the shape of frequency response of low-frequency filters limiting the frequency band. It is also shown that normalization by variance of band-limited signals leads to LSD measure anomalous behavior. Simple modification of the LSD estimate is proposed, which makes it possible to increase its statistical stability.

引用

页码：121 / 124

页数：4

共 50 条

[1] LOG-SPECTRAL AMPLITUDE ESTIMATION WITH GENERALIZED GAMMA DISTRIBUTIONS FOR SPEECH ENHANCEMENT
Borgstroem, Bengt J.
Alwan, Abeer
2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 4756 - 4759
[2] Speech enhancement based on a microphone array and log-spectral amplitude estimation
Cohen, I
Berdugo, B
22ND CONVENTION OF ELECTRICAL AND ELECTRONICS ENGINEERS IN ISRAEL, PROCEEDINGS, 2002, : 4 - 6
[3] Improved noise spectra estimation and log-spectral regression for in-car speech recognition
Li, W. (lee@sp.m.is.nagoya-u.ac.jp), Information Processing Society of Japan, IPSJ; The Database Society of Japan, DBSJ; The IEEE Computer Society; The Inst. of Elec., Info. and Com. Engineers, IEICE (IEEE Computer Society):
[4] A NOVEL APPROACH TO SOFT-MASK ESTIMATION AND LOG-SPECTRAL ENHANCEMENT FOR ROBUST SPEECH RECOGNITION
van Hout, Julien
Alwan, Abeer
2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 4105 - 4108
[5] An Improved Log-spectral Amplitude Estimator Algorithm for Speech Enhancement
Wang, Yanfen
Wu, Shouhao
Guo, Wenxiu
Ji, Jianhua
2014 IEEE INTERNATIONAL SYMPOSIUM ON BROADBAND MULTIMEDIA SYSTEMS AND BROADCASTING (BMSB), 2014,
[6] Accurate compensation in the log-spectral domain for noisy speech recognition
Afify, M
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2005, 13 (03): : 388 - 398
[7] MMSE Log-Spectral Amplitude Estimation for Single Channel Speech Enhancement under Speech Presence Uncertainty by Weibull Speech Priors
Bahrami, Mojtaba
Seyedin, Sanaz
26TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE 2018), 2018, : 749 - 754
[8] Speech Enhancement Based on Auditory Masking Properties and Log-Spectral Distance
Wang, Peihe
Wang, Yong
Liu, Hao
Sheng, Yanxiu
Wang, Xi
Wei, Zhiqiang
2013 3RD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND NETWORK TECHNOLOGY (ICCSNT), 2013, : 1060 - 1064
[9] NOISE ESTIMATION USING A CONSTRAINED SEQUENTIAL HMM IN LOG-SPECTRAL DOMAIN
Ying, Dongwen
Lu, Xugang
Li, Junfeng
Yan, Yonghong
Dang, Jianwu
Soong, Frank
2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 4553 - 4556
[10] Robust Speech Recognition Using MLP Neural Network in Log-Spectral Domain
Ghaemmaghami, Masoumeh P.
Sameti, Hossein
Razzazi, Farbod
BabaAli, Bagher
Dabbaghchian, Saeed
2009 IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY (ISSPIT 2009), 2009, : 467 - +

← 1 2 3 4 5 →