A Deep Learning-Based Approach to Non-Intrusive Objective Speech Intelligibility Estimation

• YUN Deokgyu

  Seoul National University of Science and Technology

• LEE Hannah

  Seoul National University of Science and Technology

• CHOI Seung Ho

  Seoul National University of Science and Technology

抄録

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.

収録刊行物

• IEICE Transactions on Information and Systems

  IEICE Transactions on Information and Systems E101.D (4), 1207-1208, 2018

  一般社団法人 電子情報通信学会

キーワード

• non-intrusive
• speech intelligibility
• LSTM
• RNN
• STOI

詳細情報

• CRID: 1390282679357908608
• NII論文ID: 130006602306
• DOI: 10.1587/transinf.2017edl8225
• ISSN: 17451361
• ISSN: 09168532
• Web Site: https://www.jstage.jst.go.jp/article/transinf/E101.D/4/E101.D_2017EDL8225/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
• 抄録ライセンスフラグ: 使用不可