For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A Deep Learning-Based Approach to Non-Intrusive Objective Speech Intelligibility Estimation
Deokgyu YUN Hannah LEE Seung Ho CHOI
IEICE TRANSACTIONS on Information and Systems
Publication Date: 2018/04/01
Online ISSN: 1745-1361
Type of Manuscript: LETTER
Category: Speech and Hearing
non-intrusive, speech intelligibility, LSTM, RNN, STOI,
Full Text: PDF(304.1KB)>>
This paper proposes a deep learning-based non-intrusive objective speech intelligibility estimation method based on recurrent neural network (RNN) with long short-term memory (LSTM) structure. Conventional non-intrusive estimation methods such as standard P.563 have poor estimation performance and lack of consistency, especially, in various noise and reverberation environments. The proposed method trains the LSTM RNN model parameters by utilizing the STOI that is the standard intrusive intelligibility estimation method with reference speech signal. The input and output of the LSTM RNN are the MFCC vector and the frame-wise STOI value, respectively. Experimental results show that the proposed objective intelligibility estimation method outperforms the conventional standard P.563 in various noisy and reverberant environments.