New Features Using Robust MVDR Spectrum of Filtered Autocorrelation Sequence for Robust Speech Recognition
This paper presents a novel noise-robust feature extraction method for speech recognition using the robust perceptual minimum variance distortionless response (MVDR) spectrum of temporally filtered autocorrelation sequence. The perceptual MVDR spectrum of the filtered short-time autocorrelation sequ...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2013-01-01
|
| Series: | The Scientific World Journal |
| Online Access: | http://dx.doi.org/10.1155/2013/634160 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832565609651503104 |
|---|---|
| author | Sanaz Seyedin Seyed Mohammad Ahadi Saeed Gazor |
| author_facet | Sanaz Seyedin Seyed Mohammad Ahadi Saeed Gazor |
| author_sort | Sanaz Seyedin |
| collection | DOAJ |
| description | This paper presents a novel noise-robust feature
extraction method for speech recognition using the robust perceptual minimum variance distortionless response (MVDR) spectrum of temporally filtered autocorrelation sequence. The perceptual
MVDR spectrum of the filtered short-time autocorrelation
sequence can reduce the effects of residue of the nonstationary
additive noise which remains after filtering the autocorrelation.
To achieve a more robust front-end, we also modify the robust
distortionless constraint of the MVDR spectral estimation method
via revised weighting of the subband power spectrum values
based on the sub-band signal to noise ratios (SNRs), which adjusts
it to the new proposed approach. This new function allows the
components of the input signal at the frequencies least affected by
noise to pass with larger weights and attenuates more effectively
the noisy and undesired components. This modification results
in reduction of the noise residuals of the estimated spectrum
from the filtered autocorrelation sequence, thereby leading to
a more robust algorithm. Our proposed method, when evaluated
on Aurora 2 task for recognition purposes, outperformed all Mel frequency cepstral coefficients (MFCC) as the baseline, relative autocorrelation sequence MFCC (RAS-MFCC), and the MVDR-based features in several different noisy conditions. |
| format | Article |
| id | doaj-art-d0aaba8b1ab54e3d8ed4324ce2997605 |
| institution | Kabale University |
| issn | 1537-744X |
| language | English |
| publishDate | 2013-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | The Scientific World Journal |
| spelling | doaj-art-d0aaba8b1ab54e3d8ed4324ce29976052025-02-03T01:07:09ZengWileyThe Scientific World Journal1537-744X2013-01-01201310.1155/2013/634160634160New Features Using Robust MVDR Spectrum of Filtered Autocorrelation Sequence for Robust Speech RecognitionSanaz Seyedin0Seyed Mohammad Ahadi1Saeed Gazor2Department of Electrical and Computer Engineering, Queen’s University, Kingston, ON, K7L 3N6, CanadaDepartment of Electrical Engineering, Amirkabir University of Technology, Tehran 15914, IranDepartment of Electrical and Computer Engineering, Queen’s University, Kingston, ON, K7L 3N6, CanadaThis paper presents a novel noise-robust feature extraction method for speech recognition using the robust perceptual minimum variance distortionless response (MVDR) spectrum of temporally filtered autocorrelation sequence. The perceptual MVDR spectrum of the filtered short-time autocorrelation sequence can reduce the effects of residue of the nonstationary additive noise which remains after filtering the autocorrelation. To achieve a more robust front-end, we also modify the robust distortionless constraint of the MVDR spectral estimation method via revised weighting of the subband power spectrum values based on the sub-band signal to noise ratios (SNRs), which adjusts it to the new proposed approach. This new function allows the components of the input signal at the frequencies least affected by noise to pass with larger weights and attenuates more effectively the noisy and undesired components. This modification results in reduction of the noise residuals of the estimated spectrum from the filtered autocorrelation sequence, thereby leading to a more robust algorithm. Our proposed method, when evaluated on Aurora 2 task for recognition purposes, outperformed all Mel frequency cepstral coefficients (MFCC) as the baseline, relative autocorrelation sequence MFCC (RAS-MFCC), and the MVDR-based features in several different noisy conditions.http://dx.doi.org/10.1155/2013/634160 |
| spellingShingle | Sanaz Seyedin Seyed Mohammad Ahadi Saeed Gazor New Features Using Robust MVDR Spectrum of Filtered Autocorrelation Sequence for Robust Speech Recognition The Scientific World Journal |
| title | New Features Using Robust MVDR Spectrum of Filtered Autocorrelation Sequence for Robust Speech Recognition |
| title_full | New Features Using Robust MVDR Spectrum of Filtered Autocorrelation Sequence for Robust Speech Recognition |
| title_fullStr | New Features Using Robust MVDR Spectrum of Filtered Autocorrelation Sequence for Robust Speech Recognition |
| title_full_unstemmed | New Features Using Robust MVDR Spectrum of Filtered Autocorrelation Sequence for Robust Speech Recognition |
| title_short | New Features Using Robust MVDR Spectrum of Filtered Autocorrelation Sequence for Robust Speech Recognition |
| title_sort | new features using robust mvdr spectrum of filtered autocorrelation sequence for robust speech recognition |
| url | http://dx.doi.org/10.1155/2013/634160 |
| work_keys_str_mv | AT sanazseyedin newfeaturesusingrobustmvdrspectrumoffilteredautocorrelationsequenceforrobustspeechrecognition AT seyedmohammadahadi newfeaturesusingrobustmvdrspectrumoffilteredautocorrelationsequenceforrobustspeechrecognition AT saeedgazor newfeaturesusingrobustmvdrspectrumoffilteredautocorrelationsequenceforrobustspeechrecognition |