Objective Estimation of Word Intelligibility for Noise-Reduced Speech

It is essential to ensure a satisfactory QoS (Quality of Service) when offering a speech communication system with a noise reduction algorithm. In this paper, we propose a new obejective test methodology for noise-reduced speech that estimates word intelligibility by using a distortion measure. Expe...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEICE Transactions on Communications 2008/12/01, Vol.E91.B(12), pp.4075-4077
Hauptverfasser:	YAMADA, Takeshi, KUMAKURA, Masakazu, KITAWAKI, Nobuhiko
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Applied sciences Communication systems Detection, estimation, filtering, equalization, prediction Distortion Estimates Exact sciences and technology Information, signal and communications theory Intelligibility Methodology Miscellaneous Noise Noise reduction objective estimation Operation, maintenance, reliability PESQ Signal and communications theory Signal processing Signal, noise Speech Systems, networks and services of telecommunications Telecommunications Telecommunications and information theory word intelligibility
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	It is essential to ensure a satisfactory QoS (Quality of Service) when offering a speech communication system with a noise reduction algorithm. In this paper, we propose a new obejective test methodology for noise-reduced speech that estimates word intelligibility by using a distortion measure. Experimental results confirmed that the proposed methodology gives an accurate estimate with independence of noise reduction algorithms and noise types.
ISSN:	0916-8516 1745-1345 1745-1345
DOI:	10.1093/ietcom/e91-b.12.4075