---
_id: '11939'
abstract:
- lang: eng
  text: In this paper a switching linear dynamical model (SLDM) approach for speech
    feature enhancement is improved by employing more accurate models for the dynamics
    of speech and noise. The model of the clean speech feature trajectory is improved
    by augmenting the state vector to capture information derived from the delta features.
    Further a hidden noise state variable is introduced to obtain a more elaborated
    model for the noise dynamics. Approximate Bayesian inference in the SLDM is carried
    out by a bank of extended Kalman filters, whose outputs are combined according
    to the a posteriori probability of the individual state models. Experimental results
    on the AURORA2 database show improved recognition accuracy.
author:
- first_name: Stefan
  full_name: Windmann, Stefan
  last_name: Windmann
- first_name: Reinhold
  full_name: Haeb-Umbach, Reinhold
  id: '242'
  last_name: Haeb-Umbach
citation:
  ama: 'Windmann S, Haeb-Umbach R. Modeling the dynamics of speech and noise for speech
    feature enhancement in ASR. In: <i>IEEE International Conference on Acoustics,
    Speech and Signal Processing (ICASSP 2008)</i>. ; 2008:4409-4412. doi:<a href="https://doi.org/10.1109/ICASSP.2008.4518633">10.1109/ICASSP.2008.4518633</a>'
  apa: Windmann, S., &#38; Haeb-Umbach, R. (2008). Modeling the dynamics of speech
    and noise for speech feature enhancement in ASR. In <i>IEEE International Conference
    on Acoustics, Speech and Signal Processing (ICASSP 2008)</i> (pp. 4409–4412).
    <a href="https://doi.org/10.1109/ICASSP.2008.4518633">https://doi.org/10.1109/ICASSP.2008.4518633</a>
  bibtex: '@inproceedings{Windmann_Haeb-Umbach_2008, title={Modeling the dynamics
    of speech and noise for speech feature enhancement in ASR}, DOI={<a href="https://doi.org/10.1109/ICASSP.2008.4518633">10.1109/ICASSP.2008.4518633</a>},
    booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing
    (ICASSP 2008)}, author={Windmann, Stefan and Haeb-Umbach, Reinhold}, year={2008},
    pages={4409–4412} }'
  chicago: Windmann, Stefan, and Reinhold Haeb-Umbach. “Modeling the Dynamics of Speech
    and Noise for Speech Feature Enhancement in ASR.” In <i>IEEE International Conference
    on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>, 4409–12, 2008. <a
    href="https://doi.org/10.1109/ICASSP.2008.4518633">https://doi.org/10.1109/ICASSP.2008.4518633</a>.
  ieee: S. Windmann and R. Haeb-Umbach, “Modeling the dynamics of speech and noise
    for speech feature enhancement in ASR,” in <i>IEEE International Conference on
    Acoustics, Speech and Signal Processing (ICASSP 2008)</i>, 2008, pp. 4409–4412.
  mla: Windmann, Stefan, and Reinhold Haeb-Umbach. “Modeling the Dynamics of Speech
    and Noise for Speech Feature Enhancement in ASR.” <i>IEEE International Conference
    on Acoustics, Speech and Signal Processing (ICASSP 2008)</i>, 2008, pp. 4409–12,
    doi:<a href="https://doi.org/10.1109/ICASSP.2008.4518633">10.1109/ICASSP.2008.4518633</a>.
  short: 'S. Windmann, R. Haeb-Umbach, in: IEEE International Conference on Acoustics,
    Speech and Signal Processing (ICASSP 2008), 2008, pp. 4409–4412.'
date_created: 2019-07-12T05:31:11Z
date_updated: 2022-01-06T06:51:12Z
department:
- _id: '54'
doi: 10.1109/ICASSP.2008.4518633
keyword:
- a posteriori probability
- AURORA2 database
- Bayesian inference
- Bayes methods
- channel bank filters
- extended Kalman filter banks
- hidden noise state variable
- Kalman filters
- noise dynamics
- speech enhancement
- speech feature enhancement
- speech feature trajectory
- switching linear dynamical model approach
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://groups.uni-paderborn.de/nt/pubs/2008/WiHa08-1.pdf
oa: '1'
page: 4409-4412
publication: IEEE International Conference on Acoustics, Speech and Signal Processing
  (ICASSP 2008)
status: public
title: Modeling the dynamics of speech and noise for speech feature enhancement in
  ASR
type: conference
user_id: '44006'
year: '2008'
...