Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram

Di Pan; Liang Ssili; Ying Wei; Tingfa Xu; Wang Shuangwei

doi:10.1109/CompComm.2016.7924901

Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram

Di Pan, Liang Ssili, Ying Wei, Tingfa Xu, Wang Shuangwei

School of Optics and Photonics

Northeast Normal University

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

Abstract

This paper illustrates a method to recognize nonspecific two-word Chinese vocabulary by analyzing speech signals using a narrow-band spectrogram after Fourier transform is applied to it twice. Binary width zoning line projection is carried out in the frequency domain. The projection value is treated as the characteristic value of semantic recognition feature and the support vector machine (SVM) is considered as the classifier for recognizing the semantics of non-specific two-word Chinese vocabulary. A total of 1000 voice samples were used in the simulation. The results using this method show a remarkable recognition rate of 96.0%.The proposed method provides a new way for vocabulary recognition.

Original language	English
Title of host publication	2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1233-1237
Number of pages	5
ISBN (Electronic)	9781467390262
DOIs	https://doi.org/10.1109/CompComm.2016.7924901
Publication status	Published - 10 May 2017
Event	2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Chengdu, China Duration: 14 Oct 2016 → 17 Oct 2016

Publication series

Name	2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings

Conference

Conference	2nd IEEE International Conference on Computer and Communications, ICCC 2016
Country/Territory	China
City	Chengdu
Period	14/10/16 → 17/10/16

Keywords

Binary width zoning line projection
Fourier transform twice
Narrow-band spectrogram
Support vector machine (SVM)

Access to Document

10.1109/CompComm.2016.7924901

Cite this

Pan, D., Ssili, L., Wei, Y., Xu, T., & Shuangwei, W. (2017). Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram. In 2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings (pp. 1233-1237). Article 7924901 (2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CompComm.2016.7924901

Pan, Di ; Ssili, Liang ; Wei, Ying et al. / Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram. 2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 1233-1237 (2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings).

@inproceedings{6850cf578ec64750a35eb9ebbfd0d3ac,

title = "Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram",

abstract = "This paper illustrates a method to recognize nonspecific two-word Chinese vocabulary by analyzing speech signals using a narrow-band spectrogram after Fourier transform is applied to it twice. Binary width zoning line projection is carried out in the frequency domain. The projection value is treated as the characteristic value of semantic recognition feature and the support vector machine (SVM) is considered as the classifier for recognizing the semantics of non-specific two-word Chinese vocabulary. A total of 1000 voice samples were used in the simulation. The results using this method show a remarkable recognition rate of 96.0%.The proposed method provides a new way for vocabulary recognition.",

keywords = "Binary width zoning line projection, Fourier transform twice, Narrow-band spectrogram, Support vector machine (SVM)",

author = "Di Pan and Liang Ssili and Ying Wei and Tingfa Xu and Wang Shuangwei",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2nd IEEE International Conference on Computer and Communications, ICCC 2016 ; Conference date: 14-10-2016 Through 17-10-2016",

year = "2017",

month = may,

day = "10",

doi = "10.1109/CompComm.2016.7924901",

language = "English",

series = "2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1233--1237",

booktitle = "2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings",

address = "United States",

}

Pan, D, Ssili, L, Wei, Y, Xu, T & Shuangwei, W 2017, Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram. in 2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings., 7924901, 2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 1233-1237, 2nd IEEE International Conference on Computer and Communications, ICCC 2016, Chengdu, China, 14/10/16. https://doi.org/10.1109/CompComm.2016.7924901

Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram. / Pan, Di; Ssili, Liang; Wei, Ying et al.
2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 1233-1237 7924901 (2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings).

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

TY - GEN

T1 - Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram

AU - Pan, Di

AU - Ssili, Liang

AU - Wei, Ying

AU - Xu, Tingfa

AU - Shuangwei, Wang

PY - 2017/5/10

Y1 - 2017/5/10

N2 - This paper illustrates a method to recognize nonspecific two-word Chinese vocabulary by analyzing speech signals using a narrow-band spectrogram after Fourier transform is applied to it twice. Binary width zoning line projection is carried out in the frequency domain. The projection value is treated as the characteristic value of semantic recognition feature and the support vector machine (SVM) is considered as the classifier for recognizing the semantics of non-specific two-word Chinese vocabulary. A total of 1000 voice samples were used in the simulation. The results using this method show a remarkable recognition rate of 96.0%.The proposed method provides a new way for vocabulary recognition.

AB - This paper illustrates a method to recognize nonspecific two-word Chinese vocabulary by analyzing speech signals using a narrow-band spectrogram after Fourier transform is applied to it twice. Binary width zoning line projection is carried out in the frequency domain. The projection value is treated as the characteristic value of semantic recognition feature and the support vector machine (SVM) is considered as the classifier for recognizing the semantics of non-specific two-word Chinese vocabulary. A total of 1000 voice samples were used in the simulation. The results using this method show a remarkable recognition rate of 96.0%.The proposed method provides a new way for vocabulary recognition.

KW - Binary width zoning line projection

KW - Fourier transform twice

KW - Narrow-band spectrogram

KW - Support vector machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=85020217830&partnerID=8YFLogxK

U2 - 10.1109/CompComm.2016.7924901

DO - 10.1109/CompComm.2016.7924901

M3 - Conference contribution

AN - SCOPUS:85020217830

T3 - 2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings

SP - 1233

EP - 1237

BT - 2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd IEEE International Conference on Computer and Communications, ICCC 2016

Y2 - 14 October 2016 through 17 October 2016

ER -

Pan D, Ssili L, Wei Y, Xu T, Shuangwei W. Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram. In 2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 1233-1237. 7924901. (2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings). doi: 10.1109/CompComm.2016.7924901

Recognition of non-specific two-word Chinese vocabulary by applying Fourier transform twice to the narrow-band spectrogram

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this