12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Efficient Speaker and Noise Normalization for Robust Speech Recognition

Vikas Joshi (1), Raghavendra Bilgi (1), S. Umesh (1), C. Benitez (2), L. Garcia (2)

(1) IIT Madras, India
(2) Universidad de Granada, Spain

In this paper, we describe a computationally efficient approach for combining speaker and noise normalization techniques. In particular, we combine the simple yet effective Histogram Equalization (HEQ) for noise compensation with Vocal-tract length normalization (VTLN) for speaker-normalization. While it is intuitive to remove noise first and then perform VTLN, this is difficult since HEQ performs noise compensation in the cepstral domain, while VTLN involves warping in spectral domain. In this paper, we investigate the use of the recently proposed T-VTLN approach to speaker normalization where matrix transformations are directly applied on cepstral features. We show that the speaker-specific warp-factors estimated even from noisy speech using this approach closely match those from clean-speech. Further, using sub-band HEQ (S-HEQ) and T-VTLN we get a significant relative improvement of 20% and an impressive 33.54% over baseline in recognition accuracy for Aurora-2 and Aurora-4 task respectively.

Full Paper

Bibliographic reference.  Joshi, Vikas / Bilgi, Raghavendra / Umesh, S. / Benitez, C. / Garcia, L. (2011): "Efficient speaker and noise normalization for robust speech recognition", In INTERSPEECH-2011, 2601-2604.