Detail publikace

Noise Estimation for Spectral Subtraction in Speech Processing

MOTLÍČEK, P.

Originální název

Noise Estimation for Spectral Subtraction in Speech Processing

Typ

článek ve sborníku ve WoS nebo Scopus

Jazyk

angličtina

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.

Klíčová slova

noise estimation, noise subtraction, spectral subtraction, speech recognition

Autoři

MOTLÍČEK, P.

Vydáno

10. 5. 2002

Nakladatel

Faculty of Electrical Engineering and Communication BUT

Místo

Brno

ISBN

80-214-2116-9

Kniha

Proceedings of 8th Conference STUDENT EEICT 2002

Strany počet

4

URL

http://www.fit.vutbr.cz/~motlicek/publi/2002/stc02.ps

BibTex

@inproceedings{BUT10278,
  author="Petr {Motlíček}",
  title="Noise Estimation for Spectral Subtraction in Speech Processing",
  booktitle="Proceedings of 8th Conference STUDENT EEICT 2002",
  year="2002",
  pages="4",
  publisher="Faculty of Electrical Engineering and Communication BUT",
  address="Brno",
  isbn="80-214-2116-9",
  url="http://www.fit.vutbr.cz/~motlicek/publi/2002/stc02.ps"
}