Paper Title
Intelligibility Estimation Of Speech Signal Using Hidden Markov Model

Abstract
This paper proposes a speech intelligibility estimation method based onhidden Markov model (HMM) that is widely used for speech recognition. The HMM-based method is a kind of non-intrusive speech quality measurement, which means it operates without a reference speech signal.The log-likelihood score of HMM is converted to a normalized intelligibility score. We estimate the speech intelligibility of standard low bit-rate speech coders;DoD-CELP, MELPand LPC-10. The experimental results show that the proposed HMM-based method gives improved performance than the conventional non-intrusive speech intelligibility evaluation tool. Index Terms - Speech intelligibility, HMM, low bit-rate speech coder, non-intrusive