On the effects of short-term spectrum smoothing in channel normalization

被引：10

作者：

Avendano, C

Hermansky, H

机构：

[1] Department of Electrical Engineering, Oregon Graduate Institute of Science and Technology, Portland

来源：

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING | 1997年 / 5卷 / 04期

基金：

美国国家科学基金会;

关键词：

D O I：

10.1109/89.593318

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

We present a simple analysis showing that channel normalization techniques are less effective when applied to spectral energies obtained by (weighted) summation of components of the short-time Fourier power spectrum of speech. We show that applying channel normalization processing prior to critical band integration or linear predictive all-pole modeling improves the effectiveness of the techniques.

引用

页码：372 / 374

页数：3

共 6 条

[1] COMPARISON OF PARAMETRIC REPRESENTATIONS FOR MONOSYLLABIC WORD RECOGNITION IN CONTINUOUSLY SPOKEN SENTENCES [J].

DAVIS, SB ;

MERMELSTEIN, P .

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1980, 28 (04) :357-366

[2]

HERMANSKY H, 1990, J ACOUST SOC AM, V87, P1748

[3]

HERMANSKY H, P ICSLP 92, P85

[4]

NADEU C, P ICSLP 94, P1927

[5] Training Issues and Channel Equalization Techniques for the Construction of Telephone Acoustic Models Using a High-Quality Speech Corpus [J].

Neumeyer, Leonard G. ;

Digalakis, Vassilios V. ;

Weintraub, Mitchel .

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1994, 2 (04) :590-597

[6]

ROSENBERG AE, P ICSLP 94, P1835

← 1 →