Speaker siglet detection for Business Microscope

Jun Nishimura; Nobuo Sato; Tadahiro Kuroda

doi:10.1109/ICMLA.2008.132

Speaker siglet detection for Business Microscope

Jun Nishimura, Nobuo Sato, Tadahiro Kuroda

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

4 Citations (Scopus)

Abstract

"Business Microscope "is our sensornet application in the age of knowledge, which visualizes knowledge workers' interactions by sensing their face-to-face communications. Due to the limitation of energy consumption of sensor nodes and privacy concerns, very short (0.1s) intermittently sensed (10s interval) noise-like signals called siglet is used to for detection task. To detect the speaker from the limited input, "self vs "others" classification problem is introduced. For this new classification problem, new classifier called AdaBoost LVQ is studied to explore the application of AdaBoost to reduce the error rate of the conventional classifier with strictly limited inputs. As a result, AdaBoost LVQ achieved highest recognition accuracy of 96.45% with 19.86% error rate improvement relative to best conventional classifier.

Original language	English
Title of host publication	Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008
Pages	376-381
Number of pages	6
DOIs	https://doi.org/10.1109/ICMLA.2008.132
Publication status	Published - 2008 Dec 1
Event	7th International Conference on Machine Learning and Applications, ICMLA 2008 - San Diego, CA, United States Duration: 2008 Dec 11 → 2008 Dec 13

Publication series

Name	Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008

Other

Other	7th International Conference on Machine Learning and Applications, ICMLA 2008
Country/Territory	United States
City	San Diego, CA
Period	08/12/11 → 08/12/13

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Software

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICMLA.2008.132

Cite this

Speaker siglet detection for Business Microscope. / Nishimura, Jun; Sato, Nobuo; Kuroda, Tadahiro.

Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008. 2008. p. 376-381 4725001 (Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008).

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

Nishimura, J, Sato, N & Kuroda, T 2008, Speaker siglet detection for Business Microscope. in Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008., 4725001, Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008, pp. 376-381, 7th International Conference on Machine Learning and Applications, ICMLA 2008, San Diego, CA, United States, 08/12/11. https://doi.org/10.1109/ICMLA.2008.132

@inproceedings{3134f0fe9c774f08a9e43363b067ae3c,

title = "Speaker siglet detection for Business Microscope",

abstract = "{"}Business Microscope {"}is our sensornet application in the age of knowledge, which visualizes knowledge workers' interactions by sensing their face-to-face communications. Due to the limitation of energy consumption of sensor nodes and privacy concerns, very short (0.1s) intermittently sensed (10s interval) noise-like signals called siglet is used to for detection task. To detect the speaker from the limited input, {"}self vs {"}others{"} classification problem is introduced. For this new classification problem, new classifier called AdaBoost LVQ is studied to explore the application of AdaBoost to reduce the error rate of the conventional classifier with strictly limited inputs. As a result, AdaBoost LVQ achieved highest recognition accuracy of 96.45% with 19.86% error rate improvement relative to best conventional classifier.",

author = "Jun Nishimura and Nobuo Sato and Tadahiro Kuroda",

year = "2008",

month = dec,

day = "1",

doi = "10.1109/ICMLA.2008.132",

language = "English",

isbn = "9780769534954",

series = "Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008",

pages = "376--381",

booktitle = "Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008",

note = "7th International Conference on Machine Learning and Applications, ICMLA 2008 ; Conference date: 11-12-2008 Through 13-12-2008",

}

TY - GEN

T1 - Speaker siglet detection for Business Microscope

AU - Nishimura, Jun

AU - Sato, Nobuo

AU - Kuroda, Tadahiro

PY - 2008/12/1

Y1 - 2008/12/1

N2 - "Business Microscope "is our sensornet application in the age of knowledge, which visualizes knowledge workers' interactions by sensing their face-to-face communications. Due to the limitation of energy consumption of sensor nodes and privacy concerns, very short (0.1s) intermittently sensed (10s interval) noise-like signals called siglet is used to for detection task. To detect the speaker from the limited input, "self vs "others" classification problem is introduced. For this new classification problem, new classifier called AdaBoost LVQ is studied to explore the application of AdaBoost to reduce the error rate of the conventional classifier with strictly limited inputs. As a result, AdaBoost LVQ achieved highest recognition accuracy of 96.45% with 19.86% error rate improvement relative to best conventional classifier.

AB - "Business Microscope "is our sensornet application in the age of knowledge, which visualizes knowledge workers' interactions by sensing their face-to-face communications. Due to the limitation of energy consumption of sensor nodes and privacy concerns, very short (0.1s) intermittently sensed (10s interval) noise-like signals called siglet is used to for detection task. To detect the speaker from the limited input, "self vs "others" classification problem is introduced. For this new classification problem, new classifier called AdaBoost LVQ is studied to explore the application of AdaBoost to reduce the error rate of the conventional classifier with strictly limited inputs. As a result, AdaBoost LVQ achieved highest recognition accuracy of 96.45% with 19.86% error rate improvement relative to best conventional classifier.

UR - http://www.scopus.com/inward/record.url?scp=60649097930&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=60649097930&partnerID=8YFLogxK

U2 - 10.1109/ICMLA.2008.132

DO - 10.1109/ICMLA.2008.132

M3 - Conference contribution

AN - SCOPUS:60649097930

SN - 9780769534954

T3 - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008

SP - 376

EP - 381

BT - Proceedings - 7th International Conference on Machine Learning and Applications, ICMLA 2008

T2 - 7th International Conference on Machine Learning and Applications, ICMLA 2008

Y2 - 11 December 2008 through 13 December 2008

ER -

Speaker siglet detection for Business Microscope

Abstract

Publication series

Other

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this