Application of Slope Filtering to Robust Spectral Envelope Extraction for Speech/Speaker Recognition

This paper describes a method for speech feature extraction rising morphological signal processing based oil these-called "slope transformation". The proposed approach has been used to extract the signal upper spectral envelope. Results of experiments of the automatic speech recognition (ASR) and automatic speaker identification (ASI), which were undertaken to check the performance of the presented method, have shown some evident improvements of the effectiveness of recognition of isolated words, especially for women voices. The benefits of using slope transformation was also observed in speaker identification experiment.