Bi-Spectral Acoustic Features for Robust Speech Recognition

Authors:
Kazuo Onoe;Shoei Sato;Shinichi Homma;Akio Kobayashi;Toru Imai;Tohru Takagi
Affiliations:
-;-;-;-;-;-
Venue:
IEICE - Transactions on Information and Systems
Year:
2008

Citing 3
Cited 0

Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Speech enhancement using the bispectrum

ICASSP '93 Proceedings of the Acoustics, Speech, and Signal Processing, 1993. ICASSP-93 Vol 4., 1993 IEEE International Conference on - Volume 04
Hammerstein model for speech coding

EURASIP Journal on Applied Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The extraction of acoustic features for robust speech recognition is very important for improving its performance in realistic environments. The bi-spectrum based on the Fourier transformation of the third-order cumulants expresses the non-Gaussianity and the phase information of the speech signal, showing the dependency between frequency components. In this letter, we propose a method of extracting short-time bi-spectral acoustic features with averaging features in a single frame. Merged with the conventional Mel frequency cepstral coefficients (MFCC) based on the power spectrum by the principal component analysis (PCA), the proposed features gave a 6.9% relative lower a word error rate in Japanese broadcast news transcription experiments.