A Modified Oesophageal Speech Enhancement Using Ephraim-Malah Filter For Robust Speech Recognition

摘要

This paper presents a modified Oesophageal Single Channel Speech Enhancement using Ephraim-Malah Filter for Robust Speech Recognition. An Oesophageal voice is due to the laryngectomy undergone by those persons with larynx cancer and it has extremely low intelligibility. This work was already proposed with a method of Kalman Filtering technique to improve the Speech Quality. A Novel Approach to Enhance the Speech Quality with Ephraim-Malah fdter for Robust Speech Recognition is presented in this paper where we present a speech-to-text system using isolated word recognition with voice samples in English (for the words Eight and Nine) and statistical modeling (Hidden Markov Model - HMM) for machine Speech Recognition.