Feature Extraction with Combination of HMT-Based Denoising and Weighted Filter Bank Analysis for Robust Speech Recognition(<Special Section>Corpus-Based Speech Technologies)

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, we propose a new feature extraction method that combines both HMT-based denoising and weighted filter bank analysis for robust speech recognition. The proposed method is made up of two stages in cascade. The first stage is denoising process based on the wavelet domain Hidden Markov Tree model, and the second one is the filter bank analysis with weighting coefficients obtained from the residual noise in the first stage. To evaluate performance of the proposed method, recognition experiments were carried out for additive white Gaussian and pink noise with signal-to-noise ratio from 25dB to 0dB. Experiment results demonstrate the superiority of the proposed method to the conventional ones.

• 社団法人電子情報通信学会の論文
• 2005-03-01

著者

• Bae Keunsung

  School Of Electrical Engineering And Computer Science Kyungpook National University

• Son Jongmok

  School Of Electronic And Electrical Engineering Kyungpook National University

• JUNG Sungyun

  School of Electronic and Electrical Engineering, Kyungpook National University

• Jung Sungyun

  School Of Electronic And Electrical Engineering Kyungpook National University

• Bae Keunsung

  School Of Electrical Engineering And Computer Sci. Kyungpook National Univ.

関連論文

• Microphone Array with Minimum Mean-Square Error Short-Time Spectral Amplitude Estimator for Speech Enhancement(Papers Selected from 2003 International Technical Conference on Circuits/Systems, Computers and Communications(ITC-CSCC 2003))
• Underwater Transient Signal Classification Using Binary Pattern Image of MFCC and Neural Network
• Feature Extraction with Combination of HMT-Based Denoising and Weighted Filter Bank Analysis for Robust Speech Recognition(Corpus-Based Speech Technologies)
• Robust Detection of Underwater Transient Signals Using EVRC Noise Suppression Module
• HMM-Based Underwater Target Classification with Synthesized Active Sonar Signals

スポンサーリンク