---
_id: '11745'
abstract:
- lang: eng
  text: In this paper we present a novel noise power spectral density tracking algorithm
    and its use in single-channel speech enhancement. It has the unique feature that
    it is able to track the noise statistics even if speech is dominant in a given
    time-frequency bin. As a consequence it can follow non-stationary noise superposed
    by speech, even in the critical case of rising noise power. The algorithm requires
    an initial estimate of the power spectrum of speech and is thus meant to be used
    as a postprocessor to a first speech enhancement stage. An experimental comparison
    with a state-of-the-art noise tracking algorithm demonstrates lower estimation
    errors under low SNR conditions and smaller fluctuations of the estimated values,
    resulting in improved speech quality as measured by PESQ scores.
author:
- first_name: Aleksej
  full_name: Chinaev, Aleksej
  last_name: Chinaev
- first_name: Alexander
  full_name: Krueger, Alexander
  last_name: Krueger
- first_name: Dang Hai
  full_name: Tran Vu, Dang Hai
  last_name: Tran Vu
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Chinaev A, Krueger A, Tran Vu DH, Haeb-Umbach R. Improved Noise Power Spectral
    Density Tracking by a MAP-based Postprocessor. In: <i>37th International Conference
    on Acoustics, Speech and Signal Processing (ICASSP 2012)</i>. ; 2012.'
  apa: Chinaev, A., Krueger, A., Tran Vu, D. H., &#38; Haeb-Umbach, R. (2012). Improved
    Noise Power Spectral Density Tracking by a MAP-based Postprocessor. In <i>37th
    International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)</i>.
  bibtex: '@inproceedings{Chinaev_Krueger_Tran Vu_Haeb-Umbach_2012, title={Improved
    Noise Power Spectral Density Tracking by a MAP-based Postprocessor}, booktitle={37th
    International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)},
    author={Chinaev, Aleksej and Krueger, Alexander and Tran Vu, Dang Hai and Haeb-Umbach,
    Reinhold}, year={2012} }'
  chicago: Chinaev, Aleksej, Alexander Krueger, Dang Hai Tran Vu, and Reinhold Haeb-Umbach.
    “Improved Noise Power Spectral Density Tracking by a MAP-Based Postprocessor.”
    In <i>37th International Conference on Acoustics, Speech and Signal Processing
    (ICASSP 2012)</i>, 2012.
  ieee: A. Chinaev, A. Krueger, D. H. Tran Vu, and R. Haeb-Umbach, “Improved Noise
    Power Spectral Density Tracking by a MAP-based Postprocessor,” in <i>37th International
    Conference on Acoustics, Speech and Signal Processing (ICASSP 2012)</i>, 2012.
  mla: Chinaev, Aleksej, et al. “Improved Noise Power Spectral Density Tracking by
    a MAP-Based Postprocessor.” <i>37th International Conference on Acoustics, Speech
    and Signal Processing (ICASSP 2012)</i>, 2012.
  short: 'A. Chinaev, A. Krueger, D.H. Tran Vu, R. Haeb-Umbach, in: 37th International
    Conference on Acoustics, Speech and Signal Processing (ICASSP 2012), 2012.'
date_created: 2019-07-12T05:27:26Z
date_updated: 2022-01-06T06:51:08Z
department:
- _id: '54'
keyword:
- MAP parameter estimation
- noise power estimation
- speech enhancement
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2012/ChKrDaHa12.pdf
oa: '1'
publication: 37th International Conference on Acoustics, Speech and Signal Processing
  (ICASSP 2012)
related_material:
  link:
  - description: Presentation
    relation: supplementary_material
    url: https://groups.uni-paderborn.de/nt/pubs/2012/ChKrDaHa12_Talk.pdf
status: public
title: Improved Noise Power Spectral Density Tracking by a MAP-based Postprocessor
type: conference
user_id: '44006'
year: '2012'
...