Publication detail

Fusion of diverse denoising systems for robust automatic speech recognition

DROTÁR, P. NARAYANAN, S. VAN SEGBROECK, M. KUMAR, N. AUDHKHASI, K.

Original Title

Fusion of diverse denoising systems for robust automatic speech recognition

Type

conference paper

Language

English

Original Abstract

We present a framework for combining different denoising front-ends for robust speech enhancement for recognition in noisy conditions. This is contrasted against results of optimally fusing diverse parameter settings for a single denoising algorithm. All frontends in the latter case exploit the same denoising algorithm, which combines harmonic decomposition, with noise estimation and spectral subtraction. The set of associated parameters involved in these steps are dependent on the noise conditions. Rather than explicitly tuning them, we suggest a strategy that tries to account for the trade-off between average word error rate and diversity to find an optimal subset of these parameter settings. We present the results on Aurora4 database and also compare against traditional speech enhancement methods e.g. Wiener filtering and spectral subtraction.

Keywords

decomposition, signal denoising, speech enhancement, speech recognition

Authors

DROTÁR, P.; NARAYANAN, S.; VAN SEGBROECK, M.; KUMAR, N.; AUDHKHASI, K.

RIV year

2014

Released

4. 5. 2014

Publisher

IEEE

Location

Florence

ISBN

978-1-4673-5690-9

Book

Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on

Pages from

5557

Pages to

5561

Pages count

4

URL

http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6854666&sortType%3Ddesc_p_Publication_Year%26queryText%3DDrotar

BibTex

@inproceedings{BUT110175,
  author="DROTÁR, P. and NARAYANAN, S. and VAN SEGBROECK, M. and KUMAR, N. and AUDHKHASI, K.",
  title="Fusion of diverse denoising systems for robust automatic speech recognition",
  booktitle="Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on",
  year="2014",
  volume="2014",
  pages="5557--5561",
  publisher="IEEE",
  address="Florence",
  doi="10.1109/ICASSP.2014.6854666",
  isbn="978-1-4673-5690-9",
  url="http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6854666&sortType%3Ddesc_p_Publication_Year%26queryText%3DDrotar"
}