Detail publikace

Efficient Noise Estimation and its Application for Robust Speech Recognition

Originální název

Efficient Noise Estimation and its Application for Robust Speech Recognition

Anglický název

Efficient Noise Estimation and its Application for Robust Speech Recognition

Jazyk

en

Originální abstrakt

The investigation of some well known noise estimation techniques is presented. The estimated noise is applied in our noise suppression system that is generally used for speech recognition tasks. Moreover, the algorithms are developed to take part in front-end of Distributed Speech Recognition (DSR). Therefore we have proposed some modifications of noise estimation techniques that are quickly adaptable on varying noise and do not need so much information from past segments. We also minimized the algorithmic delay. The robustness of proposed algorithms were tested under several noisy conditions.

Anglický abstrakt

The investigation of some well known noise estimation techniques is presented. The estimated noise is applied in our noise suppression system that is generally used for speech recognition tasks. Moreover, the algorithms are developed to take part in front-end of Distributed Speech Recognition (DSR). Therefore we have proposed some modifications of noise estimation techniques that are quickly adaptable on varying noise and do not need so much information from past segments. We also minimized the algorithmic delay. The robustness of proposed algorithms were tested under several noisy conditions.

BibTex


@inproceedings{BUT10277,
  author="Petr {Motlíček} and Lukáš {Burget}",
  title="Efficient Noise Estimation and its Application for Robust Speech Recognition",
  annote="The investigation of some well known noise estimation techniques
is presented. The estimated noise is applied in our noise
suppression system that is generally used for speech
recognition tasks. Moreover, the algorithms are developed to take part
in front-end of Distributed Speech Recognition (DSR). 
Therefore we have proposed some modifications of noise estimation
techniques that are quickly adaptable on varying noise and do
not need so much information from past segments. We also minimized
the algorithmic delay. The robustness of proposed algorithms
were tested under several noisy conditions.",
  address="Springer Verlag",
  booktitle="5th International Conference, TSD 2002 Brno, Czech Republic, September 2002 Proceedings",
  chapter="10277",
  institution="Springer Verlag",
  year="2002",
  month="december",
  pages="229--236",
  publisher="Springer Verlag",
  type="conference paper"
}