Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties

Ching Ta Lu; Kun Fu Tseng; Yung Yue Chen; Ling Ling Wang; Chung Lin Lei

doi:10.1109/ICASI.2016.7539737

Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties

Ching Ta Lu, Kun Fu Tseng, Yung Yue Chen, Ling Ling Wang, Chung Lin Lei

Department of Systems and Naval Mechatronic Engineering

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

4 Citations (Scopus)

Abstract

Spectral subtraction algorithms are widely used in speech enhancement. However the quality of enhanced speech is not satisfied. This study proposes using the harmonic properties of vowels to define the values of over-subtraction and spectral reservation factors by using the sigmoid function. Experimental results show that the proposed method can significantly improve the performance of a spectral-subtraction method by more reduction on musical residual noise and more reservation on consonants and weak vowels.

Original language	English
Title of host publication	2016 International Conference on Applied System Innovation, IEEE ICASI 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781467398886
DOIs	https://doi.org/10.1109/ICASI.2016.7539737
Publication status	Published - 2016 Aug 10
Event	2016 International Conference on Applied System Innovation, IEEE ICASI 2016 - Ginowan City Okinawa, Japan Duration: 2016 May 28 → 2016 Jun 1

Publication series

Name	2016 International Conference on Applied System Innovation, IEEE ICASI 2016

Other

Other	2016 International Conference on Applied System Innovation, IEEE ICASI 2016
Country	Japan
City	Ginowan City Okinawa
Period	16-05-28 → 16-06-01

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Computer Science Applications
Control and Systems Engineering
Social Sciences (miscellaneous)
Business, Management and Accounting (miscellaneous)
Electrical and Electronic Engineering
Control and Optimization

Access to Document

10.1109/ICASI.2016.7539737

Fingerprint Dive into the research topics of 'Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties'. Together they form a unique fingerprint.

Cite this

Lu, C. T., Tseng, K. F., Chen, Y. Y., Wang, L. L., & Lei, C. L. (2016). Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties. In 2016 International Conference on Applied System Innovation, IEEE ICASI 2016 [7539737] (2016 International Conference on Applied System Innovation, IEEE ICASI 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASI.2016.7539737

Lu, Ching Ta ; Tseng, Kun Fu ; Chen, Yung Yue ; Wang, Ling Ling ; Lei, Chung Lin. / Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties. 2016 International Conference on Applied System Innovation, IEEE ICASI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. (2016 International Conference on Applied System Innovation, IEEE ICASI 2016).

@inproceedings{f6c5633ab45d42ebbaa2cc501dc69955,

title = "Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties",

abstract = "Spectral subtraction algorithms are widely used in speech enhancement. However the quality of enhanced speech is not satisfied. This study proposes using the harmonic properties of vowels to define the values of over-subtraction and spectral reservation factors by using the sigmoid function. Experimental results show that the proposed method can significantly improve the performance of a spectral-subtraction method by more reduction on musical residual noise and more reservation on consonants and weak vowels.",

author = "Lu, {Ching Ta} and Tseng, {Kun Fu} and Chen, {Yung Yue} and Wang, {Ling Ling} and Lei, {Chung Lin}",

year = "2016",

month = aug,

day = "10",

doi = "10.1109/ICASI.2016.7539737",

language = "English",

series = "2016 International Conference on Applied System Innovation, IEEE ICASI 2016",

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

booktitle = "2016 International Conference on Applied System Innovation, IEEE ICASI 2016",

address = "United States",

note = "2016 International Conference on Applied System Innovation, IEEE ICASI 2016 ; Conference date: 28-05-2016 Through 01-06-2016",

}

Lu, CT, Tseng, KF, Chen, YY, Wang, LL & Lei, CL 2016, Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties. in 2016 International Conference on Applied System Innovation, IEEE ICASI 2016., 7539737, 2016 International Conference on Applied System Innovation, IEEE ICASI 2016, Institute of Electrical and Electronics Engineers Inc., 2016 International Conference on Applied System Innovation, IEEE ICASI 2016, Ginowan City Okinawa, Japan, 16-05-28. https://doi.org/10.1109/ICASI.2016.7539737

Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties. / Lu, Ching Ta; Tseng, Kun Fu; Chen, Yung Yue; Wang, Ling Ling; Lei, Chung Lin.

2016 International Conference on Applied System Innovation, IEEE ICASI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. 7539737 (2016 International Conference on Applied System Innovation, IEEE ICASI 2016).

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

TY - GEN

T1 - Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties

AU - Lu, Ching Ta

AU - Tseng, Kun Fu

AU - Chen, Yung Yue

AU - Wang, Ling Ling

AU - Lei, Chung Lin

PY - 2016/8/10

Y1 - 2016/8/10

N2 - Spectral subtraction algorithms are widely used in speech enhancement. However the quality of enhanced speech is not satisfied. This study proposes using the harmonic properties of vowels to define the values of over-subtraction and spectral reservation factors by using the sigmoid function. Experimental results show that the proposed method can significantly improve the performance of a spectral-subtraction method by more reduction on musical residual noise and more reservation on consonants and weak vowels.

AB - Spectral subtraction algorithms are widely used in speech enhancement. However the quality of enhanced speech is not satisfied. This study proposes using the harmonic properties of vowels to define the values of over-subtraction and spectral reservation factors by using the sigmoid function. Experimental results show that the proposed method can significantly improve the performance of a spectral-subtraction method by more reduction on musical residual noise and more reservation on consonants and weak vowels.

UR - http://www.scopus.com/inward/record.url?scp=84988481795&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988481795&partnerID=8YFLogxK

U2 - 10.1109/ICASI.2016.7539737

DO - 10.1109/ICASI.2016.7539737

M3 - Conference contribution

AN - SCOPUS:84988481795

T3 - 2016 International Conference on Applied System Innovation, IEEE ICASI 2016

BT - 2016 International Conference on Applied System Innovation, IEEE ICASI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 International Conference on Applied System Innovation, IEEE ICASI 2016

Y2 - 28 May 2016 through 1 June 2016

ER -

Lu CT, Tseng KF, Chen YY, Wang LL, Lei CL. Speech enhancement using spectral subtraction algorithm with over-subtraction and reservation factors adapted by harmonic properties. In 2016 International Conference on Applied System Innovation, IEEE ICASI 2016. Institute of Electrical and Electronics Engineers Inc. 2016. 7539737. (2016 International Conference on Applied System Innovation, IEEE ICASI 2016). https://doi.org/10.1109/ICASI.2016.7539737