Pitch restoration for robust speech recognition

Abstract

The changing on speech peaks structure is perhaps the most important cause of degradation of speech recognition systems under adverse conditions. Another drawback concerned to the additive noise effect occurs on the flat spectral zones which are usually raised. These combined effects on both the peaked and the flat spectral zones can be alleviated by trying to restore its original structure, which assumes noise knowledge. This paper suggests noise estimation in a frame by frame basis by assuming the clean database as lightly corrupted. The noise estimate is then used to restore both the peaked and the flat spectral zones of the speech spectrum. This algorithm was implemented over a baseline spectral normalisation method. This method was developed by taking into consideration that, while the speech regions with less energy need more robustness, since in these regions the noise is more dominant, the “peaked” spectral regions which are the most reliable due to the higher speech energy must also be preserved as much as possible by the feature extraction process.