hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.1001298

Role of Spectral Peaks in Autocoorelation Domain for Robust Speech Recognition

Poonam Bansal
Amita Dev
Shail Bala Jain

Puni tekst: engleski, pdf (394 KB) str. 295-303 preuzimanja: 697* citiraj
APA 6th Edition
Bansal, P., Dev, A. i Jain, S.B. (2009). Role of Spectral Peaks in Autocoorelation Domain for Robust Speech Recognition. Journal of computing and information technology, 17 (3), 295-303. https://doi.org/10.2498/cit.1001298
MLA 8th Edition
Bansal, Poonam, et al. "Role of Spectral Peaks in Autocoorelation Domain for Robust Speech Recognition." Journal of computing and information technology, vol. 17, br. 3, 2009, str. 295-303. https://doi.org/10.2498/cit.1001298. Citirano 12.12.2019.
Chicago 17th Edition
Bansal, Poonam, Amita Dev i Shail Bala Jain. "Role of Spectral Peaks in Autocoorelation Domain for Robust Speech Recognition." Journal of computing and information technology 17, br. 3 (2009): 295-303. https://doi.org/10.2498/cit.1001298
Harvard
Bansal, P., Dev, A., i Jain, S.B. (2009). 'Role of Spectral Peaks in Autocoorelation Domain for Robust Speech Recognition', Journal of computing and information technology, 17(3), str. 295-303. https://doi.org/10.2498/cit.1001298
Vancouver
Bansal P, Dev A, Jain SB. Role of Spectral Peaks in Autocoorelation Domain for Robust Speech Recognition. Journal of computing and information technology [Internet]. 2009 [pristupljeno 12.12.2019.];17(3):295-303. https://doi.org/10.2498/cit.1001298
IEEE
P. Bansal, A. Dev i S.B. Jain, "Role of Spectral Peaks in Autocoorelation Domain for Robust Speech Recognition", Journal of computing and information technology, vol.17, br. 3, str. 295-303, 2009. [Online]. https://doi.org/10.2498/cit.1001298

Sažetak
This paper presents a new front-end for robust speech recognition. This new front-end scenario focuses on the spectral features of the filtered speech signals in the autocorrelation domain. The autocorrelation domain is well known for its pole preserving and noise separation properties. In this paper we will use the autocorrelation domain as an appropriate candidate for robust feature extraction. The proposed method introduces a novel representation of speech for the cases where the speech signal is corrupted by additive noises. In this method, the speech features are computed by reducing additive noise effects via an initial filtering stage, followed by the extraction of autocorrelation spectrum peaks. Robust features based on theses peaks are derived by assuming that the corrupting noise is stationary in nature. A task of speaker-independent isolated-word recognition is used to demonstrate the efficiency of these robust features. The cases of white noise and colored noise such as factory, babble and F16 are tested. Experimental results show significant improvement in comparison to the results obtained using traditional front end methods. Further enhancement has been done by applying cepstral mean normalization (CMN) on the above extracted features.

Hrčak ID: 44867

URI
https://hrcak.srce.hr/44867

Posjeta: 830 *