AES E-Library

Y. Cao, S. Sridharan, and M. Moody, "Voiced/Unvoiced/Silence Classification of Noisy Speech in Real Time Audio Signal Processing," Paper 4045, (1995 March.). doi: Y. Cao, S. Sridharan, and M. Moody, "Voiced/Unvoiced/Silence Classification of Noisy Speech in Real Time Audio Signal Processing," Paper 4045, (1995 March.). doi:
Abstract: The classification of noisy speech signal into voiced, unvoiced, and silence provides a preliminary acoustic segmentation for audio signal processing applications, such as digital coding, speech enhancement, and identification. The proposed technique employs a two-staged structure and uses the normalized segmental energy, normalized partial sum of autocorrelation coefficients, and spectral envelope pattern matching as the measurement criteria to classify the voiced and unvoiced speech segments from background noise. The reference noise pattern is updated by incoming silent segments and the classifier can work in real time. Simulation results have shown that this technique is robust even if the audio signal is corrupted by heavy broadband noise.

@article{cao1995voiced/unvoiced/silence,
author={cao, yuchang and sridharan, sridha and moody, miles},
journal={journal of the audio engineering society},
title={voiced/unvoiced/silence classification of noisy speech in real time audio signal processing},
year={1995},
volume={},
number={},
pages={},
doi={},
month={march},} @article{cao1995voiced/unvoiced/silence,
author={cao, yuchang and sridharan, sridha and moody, miles},
journal={journal of the audio engineering society},
title={voiced/unvoiced/silence classification of noisy speech in real time audio signal processing},
year={1995},
volume={},
number={},
pages={},
doi={},
month={march},
abstract={the classification of noisy speech signal into voiced, unvoiced, and silence provides a preliminary acoustic segmentation for audio signal processing applications, such as digital coding, speech enhancement, and identification. the proposed technique employs a two-staged structure and uses the normalized segmental energy, normalized partial sum of autocorrelation coefficients, and spectral envelope pattern matching as the measurement criteria to classify the voiced and unvoiced speech segments from background noise. the reference noise pattern is updated by incoming silent segments and the classifier can work in real time. simulation results have shown that this technique is robust even if the audio signal is corrupted by heavy broadband noise.},}

TY - paper
TI - Voiced/Unvoiced/Silence Classification of Noisy Speech in Real Time Audio Signal Processing
SP - EP -
AU - Cao, Yuchang
AU - Sridharan, Sridha
AU - Moody, Miles
PY - 1995
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - March 1995 TY - paper
TI - Voiced/Unvoiced/Silence Classification of Noisy Speech in Real Time Audio Signal Processing
SP - EP -
AU - Cao, Yuchang
AU - Sridharan, Sridha
AU - Moody, Miles
PY - 1995
JO - Journal of the Audio Engineering Society
IS -
VO -
VL -
Y1 - March 1995
AB - The classification of noisy speech signal into voiced, unvoiced, and silence provides a preliminary acoustic segmentation for audio signal processing applications, such as digital coding, speech enhancement, and identification. The proposed technique employs a two-staged structure and uses the normalized segmental energy, normalized partial sum of autocorrelation coefficients, and spectral envelope pattern matching as the measurement criteria to classify the voiced and unvoiced speech segments from background noise. The reference noise pattern is updated by incoming silent segments and the classifier can work in real time. Simulation results have shown that this technique is robust even if the audio signal is corrupted by heavy broadband noise.