Voiced/Unvoiced/Silence Classification of Noisy Speech in Real Time Audio Signal Processing

Cao Y, Sridharan S, Moody M. Voiced/Unvoiced/Silence Classification of Noisy Speech in Real Time Audio Signal Processing. In: AES Convention 5r. Audio Engineering Society; 1995. Paper 4045. Available from: https://aes.org/publications/elibrary-page/?id=7721

@inproceedings{Cao1995_7721,
  author = {Cao, Yuchang and Sridharan, Sridha and Moody, Miles},
  title = {{Voiced/Unvoiced/Silence Classification of Noisy Speech in Real Time Audio Signal Processing}},
  booktitle = {AES Convention 5r},
  note = {Paper 4045},
  year = {1995},
  month = mar,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=7721}
}

TY  - CPAPER
TI  - Voiced/Unvoiced/Silence Classification of Noisy Speech in Real Time Audio Signal Processing
AU  - Cao, Yuchang
AU  - Sridharan, Sridha
AU  - Moody, Miles
T2  - AES Convention 5r
M1  - Paper 4045
PY  - 1995
DA  - 1995/03/06
UR  - https://aes.org/publications/elibrary-page/?id=7721
PB  - Audio Engineering Society
LA  - en
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.
ER  -