Sparse NMF based speech enhancement with bases update

Sparse NMF based speech enhancement with bases update In this paper, a combination of methods based on statistical modelling and Non-negative Matrix Factorization (NMF) for speech enhancement using speech and noise bases with on-line update is proposed. Template-based approaches are known to be more robust in the presence of non-stationary noises than methods based on statistical modeling. However, template-based approaches depend on a-priori information. The drawbacks of both the approaches can be avoided by combining them. In NMF approach, speech bases and noise bases are simultaneously adapted to further improve the performance. The proposed method outperforms other benchmark algorithms in terms of perceptual evaluation of speech quality (PESQ) and source-to-distortion ratio (SDR) in stationary and non-stationary noise environment conditions with matched and mismatched noise basis. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Speech Technology Springer Journals

Sparse NMF based speech enhancement with bases update

Loading next page...
 
/lp/springer_journal/sparse-nmf-based-speech-enhancement-with-bases-update-cTLV2FVkr9
Publisher
Springer US
Copyright
Copyright © 2017 by Springer Science+Business Media New York
Subject
Engineering; Signal,Image and Speech Processing; Social Sciences, general; Artificial Intelligence (incl. Robotics)
ISSN
1381-2416
eISSN
1572-8110
D.O.I.
10.1007/s10772-017-9418-0
Publisher site
See Article on Publisher Site

Abstract

In this paper, a combination of methods based on statistical modelling and Non-negative Matrix Factorization (NMF) for speech enhancement using speech and noise bases with on-line update is proposed. Template-based approaches are known to be more robust in the presence of non-stationary noises than methods based on statistical modeling. However, template-based approaches depend on a-priori information. The drawbacks of both the approaches can be avoided by combining them. In NMF approach, speech bases and noise bases are simultaneously adapted to further improve the performance. The proposed method outperforms other benchmark algorithms in terms of perceptual evaluation of speech quality (PESQ) and source-to-distortion ratio (SDR) in stationary and non-stationary noise environment conditions with matched and mismatched noise basis.

Journal

International Journal of Speech TechnologySpringer Journals

Published: May 9, 2017

References

You’re reading a free preview. Subscribe to read the entire article.


DeepDyve is your
personal research library

It’s your single place to instantly
discover and read the research
that matters to you.

Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.

All for just $49/month

Explore the DeepDyve Library

Search

Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly

Organize

Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.

Access

Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.

Your journals are on DeepDyve

Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.

All the latest content is available, no embargo periods.

See the journals in your area

DeepDyve

Freelancer

DeepDyve

Pro

Price

FREE

$49/month
$360/year

Save searches from
Google Scholar,
PubMed

Create lists to
organize your research

Export lists, citations

Read DeepDyve articles

Abstract access only

Unlimited access to over
18 million full-text articles

Print

20 pages / month

PDF Discount

20% off