Detail publikace

Noise Estimation for Spectral Subtraction in Speech Processing

Originální název

Noise Estimation for Spectral Subtraction in Speech Processing

Anglický název

Noise Estimation for Spectral Subtraction in Speech Processing

Jazyk

en

Originální abstrakt

This contribution presents two often used algorithms for enhancement of noisy speech signal in spectral domain. These algorithms do not differ in removing noise from the input speech. Different parts are processes of noise estimation which are used before noise suppression. Both algorithms have ability to track non stationary noise signal and do not need voice activity detector. Both methods have been tested in front-end distributed speech recognition (DSR) system. Algorithm parameters, as CPU complexity or memory requirements, as well as the need of delay in processing, will be discussed.

Anglický abstrakt

This contribution presents two often used algorithms for enhancement of noisy speech signal in spectral domain. These algorithms do not differ in removing noise from the input speech. Different parts are processes of noise estimation which are used before noise suppression. Both algorithms have ability to track non stationary noise signal and do not need voice activity detector. Both methods have been tested in front-end distributed speech recognition (DSR) system. Algorithm parameters, as CPU complexity or memory requirements, as well as the need of delay in processing, will be discussed.

BibTex


@inproceedings{BUT10278,
  author="Petr {Motlíček}",
  title="Noise Estimation for Spectral Subtraction in Speech Processing",
  annote="This contribution presents two often used algorithms for enhancement of noisy speech signal in spectral domain. These algorithms do not differ in removing noise from the input speech. Different parts are processes of noise estimation which are used before noise suppression. Both algorithms have ability to track non stationary noise signal and do not need voice activity detector. Both methods have been tested in front-end distributed speech recognition (DSR) system. Algorithm parameters, as CPU complexity or memory requirements, as well as the need of delay in processing, will be discussed.",
  address="Faculty of Electrical Engineering and Communication BUT",
  booktitle="Proceedings of 8th Conference STUDENT EEICT 2002",
  chapter="10278",
  institution="Faculty of Electrical Engineering and Communication BUT",
  year="2002",
  month="may",
  pages="0",
  publisher="Faculty of Electrical Engineering and Communication BUT",
  type="conference paper"
}