On a robust ASR based on robust complex speech analysis

Abstract

The European Telecommunications Standards Institute (ETSI) standardized the advanced front-end (AFE) for automatic speech recognition (ASR). In the AFE a speech enhancement is realized by an iterative Wiener filter (IWF) in which a smoothed FFT spectrum over adjacent frames is used to design the filter. On the other hand, we have previously proposed robust time-varying complex AR (TV-CAR) speech analysis and evaluated the performance of speech processing such as F0 estimation and speech enhancement. TV-CAR analysis can estimate more accurate spectrum than FFT, especially in low frequencies because of the nature of the analytic signal. In addition, TV-CAR can estimate more accurate speech spectrum against additive noise. In this paper, a time-invariant version of wide-band TV-CAR analysis based on robust Extended Least Square (ELS) approach is introduced to the IWF in the AFE and is evaluated using the CENSREC-2 database.