A model for time-varying quality of speech services

Chen Zhan; Hidenori Nakazato

doi:10.1109/GLOCOM.2005.1577626

A model for time-varying quality of speech services

Chen Zhan^*, Hidenori Nakazato

^*Corresponding author for this work

School of Fundamental Science and Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

10 Citations (Scopus)

Abstract

Speech services are widely deployed on new communication infrastructures. However, compared with traditional infrastructures, the ever varying conditions are native of these new infrastructures. Modeling the time-varying speech quality becomes an urgent issue. This paper proposes a computable model for time-varying speech quality evaluation, called M-Model. Considering the time-varying issue, EWMA is used in the model. M-Model is validated by a subjective experiment. The model indicates that time-varying quality with extremely high frequency will not affect perceived quality at all. In addition, we observed that the recency effect influences not only the perceived overall quality but also the perceived instantaneous quality.

Original language	English
Title of host publication	GLOBECOM'05
Subtitle of host publication	IEEE Global Telecommunications Conference, 2005
Pages	240-244
Number of pages	5
DOIs	https://doi.org/10.1109/GLOCOM.2005.1577626
Publication status	Published - 2005 Dec 1
Event	GLOBECOM'05: IEEE Global Telecommunications Conference, 2005 - St. Louis, MO, United States Duration: 2005 Nov 28 → 2005 Dec 2

Publication series

Name	GLOBECOM - IEEE Global Telecommunications Conference
Volume	1

Conference

Conference	GLOBECOM'05: IEEE Global Telecommunications Conference, 2005
Country/Territory	United States
City	St. Louis, MO
Period	05/11/28 → 05/12/2

ASJC Scopus subject areas

Engineering(all)

Access to Document

10.1109/GLOCOM.2005.1577626

Cite this

Zhan, C & Nakazato, H 2005, A model for time-varying quality of speech services. in GLOBECOM'05: IEEE Global Telecommunications Conference, 2005., 1577626, GLOBECOM - IEEE Global Telecommunications Conference, vol. 1, pp. 240-244, GLOBECOM'05: IEEE Global Telecommunications Conference, 2005, St. Louis, MO, United States, 05/11/28. https://doi.org/10.1109/GLOCOM.2005.1577626

@inproceedings{370ecc6c86444209a3300c132edfc719,

title = "A model for time-varying quality of speech services",

abstract = "Speech services are widely deployed on new communication infrastructures. However, compared with traditional infrastructures, the ever varying conditions are native of these new infrastructures. Modeling the time-varying speech quality becomes an urgent issue. This paper proposes a computable model for time-varying speech quality evaluation, called M-Model. Considering the time-varying issue, EWMA is used in the model. M-Model is validated by a subjective experiment. The model indicates that time-varying quality with extremely high frequency will not affect perceived quality at all. In addition, we observed that the recency effect influences not only the perceived overall quality but also the perceived instantaneous quality.",

author = "Chen Zhan and Hidenori Nakazato",

year = "2005",

month = dec,

day = "1",

doi = "10.1109/GLOCOM.2005.1577626",

language = "English",

isbn = "0780394143",

series = "GLOBECOM - IEEE Global Telecommunications Conference",

pages = "240--244",

booktitle = "GLOBECOM'05",

note = "GLOBECOM'05: IEEE Global Telecommunications Conference, 2005 ; Conference date: 28-11-2005 Through 02-12-2005",

}

TY - GEN

T1 - A model for time-varying quality of speech services

AU - Zhan, Chen

AU - Nakazato, Hidenori

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Speech services are widely deployed on new communication infrastructures. However, compared with traditional infrastructures, the ever varying conditions are native of these new infrastructures. Modeling the time-varying speech quality becomes an urgent issue. This paper proposes a computable model for time-varying speech quality evaluation, called M-Model. Considering the time-varying issue, EWMA is used in the model. M-Model is validated by a subjective experiment. The model indicates that time-varying quality with extremely high frequency will not affect perceived quality at all. In addition, we observed that the recency effect influences not only the perceived overall quality but also the perceived instantaneous quality.

AB - Speech services are widely deployed on new communication infrastructures. However, compared with traditional infrastructures, the ever varying conditions are native of these new infrastructures. Modeling the time-varying speech quality becomes an urgent issue. This paper proposes a computable model for time-varying speech quality evaluation, called M-Model. Considering the time-varying issue, EWMA is used in the model. M-Model is validated by a subjective experiment. The model indicates that time-varying quality with extremely high frequency will not affect perceived quality at all. In addition, we observed that the recency effect influences not only the perceived overall quality but also the perceived instantaneous quality.

UR - http://www.scopus.com/inward/record.url?scp=33846624761&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33846624761&partnerID=8YFLogxK

U2 - 10.1109/GLOCOM.2005.1577626

DO - 10.1109/GLOCOM.2005.1577626

M3 - Conference contribution

AN - SCOPUS:33846624761

SN - 0780394143

SN - 9780780394148

T3 - GLOBECOM - IEEE Global Telecommunications Conference

SP - 240

EP - 244

BT - GLOBECOM'05

T2 - GLOBECOM'05: IEEE Global Telecommunications Conference, 2005

Y2 - 28 November 2005 through 2 December 2005

ER -

A model for time-varying quality of speech services

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this