Title :
The effects of subtractive-type speech enhancement/noise reduction algorithms on parameter estimation for improved recognition and coding in high noise environments
Author :
Kushner, William M. ; Goncharoff, Vladimir ; Wu, Chung ; Nguyen, Vien ; Damoulakis, John N.
Author_Institution :
Martin Marietta Aero & Naval Syst., Glen Burnie, MD, USA
Abstract :
The authors present the results of a study designed to investigate the effects of subtractive-type noise reduction algorithms on LPC-based spectral parameter estimation as related to the performance of speech processors operating with input SNRs of 15 dB and below. Subtractive noise preprocessing greatly improves the SNR, but system performance improvement is not commensurate. LPC spectral estimation is affected by the character of the residual noise which exhibits greater variance and spectral granularity than the original broadband noise. The study shows that removing less than the full amount of noise and whitening it improves spectral estimation and speech device performance. Techniques and performance results are presented
Keywords :
encoding; filtering and prediction theory; interference suppression; parameter estimation; speech analysis and processing; speech recognition; 15 dB; LPC-based spectral parameter estimation; broadband noise; character; high noise environments; input SNRs; residual noise; spectral granularity; speech coding; speech device performance; speech processors; speech recognition; subtractive noise preprocessing; subtractive-type noise reduction algorithms; subtractive-type speech enhancement algorithms; variance; whitening; Acoustic noise; Cepstral analysis; Linear predictive coding; Noise reduction; Parameter estimation; Signal to noise ratio; Speech coding; Speech enhancement; Speech processing; Speech recognition;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1989. ICASSP-89., 1989 International Conference on
Conference_Location :
Glasgow
DOI :
10.1109/ICASSP.1989.266402
