A Multimicrophone Voice Activity Detection System Based on Mutual Information

Talantzis F, Constantinides AG. A Multimicrophone Voice Activity Detection System Based on Mutual Information. J Audio Eng Soc. 2009;57(11):937-950. Available from: https://aes.org/publications/elibrary-page/?id=15230

@article{Talantzis2009_15230,
  author = {Talantzis, Fotios and Constantinides, Anthony G.},
  title = {{A Multimicrophone Voice Activity Detection System Based on Mutual Information}},
  journal = {Journal of the Audio Engineering Society},
  volume = {57},
  number = {11},
  pages = {937--950},
  year = {2009},
  month = nov,
  publisher = {Audio Engineering Society},
  url = {https://aes.org/publications/elibrary-page/?id=15230}
}

TY  - JOUR
TI  - A Multimicrophone Voice Activity Detection System Based on Mutual Information
AU  - Talantzis, Fotios
AU  - Constantinides, Anthony G.
T2  - Journal of the Audio Engineering Society
J2  - J. Audio Eng. Soc.
VL  - 57
IS  - 11
SP  - 937
EP  - 950
PY  - 2009
DA  - 2009/11/06
UR  - https://aes.org/publications/elibrary-page/?id=15230
PB  - Audio Engineering Society
LA  - en
AB  - In many applications, such as hands-free telephony and smart environments, there is a need to distinguish voice from background noise and reverberation. A proposed system computes an information-theoretic coherency between multiple microphones in order to detect near-field speech. The system performance was compared to that of a reference case in both simulations and experiments. While all such systems degrade with increasing noise and reverberation, the proposed system proved to be more robust under adverse conditions.
ER  -