Speech enhancement by Kalman filtering with residual noise clipping

Wen Jin, Michael S Scordilis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

In this paper, we develop an improved speech enhancement system based on Kalman Filtering (KF) that processes the linear prediction (LP) residual of voiced speech. For input frames where voiced speech is present, the LP residuals are clipped to maintain the peaks where the major excitation pulses are located. The proposed algorithm differs from the conventional Kalman Filtering algorithms in that it includes this quasi-periodic term in the process equation for voiced speech frames. The quality of the resulting enhanced speech is evaluated by means of Signal-to-Noise-Ratio (SNR) and ITU-PESQ scores. Experimental results indicate that the proposed algorithm achieves consistent improvement in output speech quality when compared to conventional KF methods.

Original languageEnglish (US)
Title of host publicationConference Proceedings - IEEE SOUTHEASTCON
EditorsY. Levy
Pages225-228
Number of pages4
StatePublished - 2005
EventIEEE Southeastcon 2005: Excellence in Engineering, Science and Technology - Ft. Lauderdale, United Kingdom
Duration: Apr 8 2005Apr 10 2005

Other

OtherIEEE Southeastcon 2005: Excellence in Engineering, Science and Technology
CountryUnited Kingdom
CityFt. Lauderdale
Period4/8/054/10/05

Fingerprint

Speech enhancement
Signal to noise ratio

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Jin, W., & Scordilis, M. S. (2005). Speech enhancement by Kalman filtering with residual noise clipping. In Y. Levy (Ed.), Conference Proceedings - IEEE SOUTHEASTCON (pp. 225-228)

Speech enhancement by Kalman filtering with residual noise clipping. / Jin, Wen; Scordilis, Michael S.

Conference Proceedings - IEEE SOUTHEASTCON. ed. / Y. Levy. 2005. p. 225-228.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jin, W & Scordilis, MS 2005, Speech enhancement by Kalman filtering with residual noise clipping. in Y Levy (ed.), Conference Proceedings - IEEE SOUTHEASTCON. pp. 225-228, IEEE Southeastcon 2005: Excellence in Engineering, Science and Technology, Ft. Lauderdale, United Kingdom, 4/8/05.
Jin W, Scordilis MS. Speech enhancement by Kalman filtering with residual noise clipping. In Levy Y, editor, Conference Proceedings - IEEE SOUTHEASTCON. 2005. p. 225-228
Jin, Wen ; Scordilis, Michael S. / Speech enhancement by Kalman filtering with residual noise clipping. Conference Proceedings - IEEE SOUTHEASTCON. editor / Y. Levy. 2005. pp. 225-228
@inproceedings{b3c4b4655e284fe0adf1ad8c29334668,
title = "Speech enhancement by Kalman filtering with residual noise clipping",
abstract = "In this paper, we develop an improved speech enhancement system based on Kalman Filtering (KF) that processes the linear prediction (LP) residual of voiced speech. For input frames where voiced speech is present, the LP residuals are clipped to maintain the peaks where the major excitation pulses are located. The proposed algorithm differs from the conventional Kalman Filtering algorithms in that it includes this quasi-periodic term in the process equation for voiced speech frames. The quality of the resulting enhanced speech is evaluated by means of Signal-to-Noise-Ratio (SNR) and ITU-PESQ scores. Experimental results indicate that the proposed algorithm achieves consistent improvement in output speech quality when compared to conventional KF methods.",
author = "Wen Jin and Scordilis, {Michael S}",
year = "2005",
language = "English (US)",
pages = "225--228",
editor = "Y. Levy",
booktitle = "Conference Proceedings - IEEE SOUTHEASTCON",

}

TY - GEN

T1 - Speech enhancement by Kalman filtering with residual noise clipping

AU - Jin, Wen

AU - Scordilis, Michael S

PY - 2005

Y1 - 2005

N2 - In this paper, we develop an improved speech enhancement system based on Kalman Filtering (KF) that processes the linear prediction (LP) residual of voiced speech. For input frames where voiced speech is present, the LP residuals are clipped to maintain the peaks where the major excitation pulses are located. The proposed algorithm differs from the conventional Kalman Filtering algorithms in that it includes this quasi-periodic term in the process equation for voiced speech frames. The quality of the resulting enhanced speech is evaluated by means of Signal-to-Noise-Ratio (SNR) and ITU-PESQ scores. Experimental results indicate that the proposed algorithm achieves consistent improvement in output speech quality when compared to conventional KF methods.

AB - In this paper, we develop an improved speech enhancement system based on Kalman Filtering (KF) that processes the linear prediction (LP) residual of voiced speech. For input frames where voiced speech is present, the LP residuals are clipped to maintain the peaks where the major excitation pulses are located. The proposed algorithm differs from the conventional Kalman Filtering algorithms in that it includes this quasi-periodic term in the process equation for voiced speech frames. The quality of the resulting enhanced speech is evaluated by means of Signal-to-Noise-Ratio (SNR) and ITU-PESQ scores. Experimental results indicate that the proposed algorithm achieves consistent improvement in output speech quality when compared to conventional KF methods.

UR - http://www.scopus.com/inward/record.url?scp=27544472826&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27544472826&partnerID=8YFLogxK

M3 - Conference contribution

SP - 225

EP - 228

BT - Conference Proceedings - IEEE SOUTHEASTCON

A2 - Levy, Y.

ER -