Effective Energy Feature Compensation Using Modified Log-energy Dynamic Range Normalization for Robust Speech Recognition(Fundamental Theories for Communications)

スポンサーリンク

概要

• 論文の詳細を見る

• This paper proposes effective energy feature normalization methods for robust speech recognition in noisy environments. We first develop an energy subtraction method and a modified method for the Log-energy Dynamic Range Normalization (ERN) using inverse function. We then present the hybrid method combining the energy subtraction and the modified ERN. Using Aurora2.0 database for representative evaluations, a significant performance improvement over the ERN method is demonstrated.

• 社団法人電子情報通信学会の論文
• 2007-06-01

著者

• Ko Hanseok

  Department Of Electronics And Computer Engineering Korea University

• LEE Yoonjae

  Department of Electronics and Computer Engineering, Korea University

• Lee Yoonjae

  Department Of Electronics And Computer Engineering Korea University

関連論文

• Effective Multi-Vehicle Tracking in Nighttime Condition Using Imaging Sensors(Image Processing, Image pattern Recognition)
• Harmonic Components Based Post-Filter Design for Residual Echo Suppression
• W-Disjoint Orthogonality Based Residual Acoustic Echo Cancellation for Hands-Free Communication
• Masking Property Based Residual Acoustic Echo Cancellation for Hands-Free Communication in Automobile Environment
• Effective Energy Feature Compensation Using Modified Log-energy Dynamic Range Normalization for Robust Speech Recognition(Fundamental Theories for Communications)
• Bayesian Confidence Scoring and Adaptation Techniques for Speech Recognition(Multimedia Systems for Communications)
• Effective Tracking for Maneuvering Mobile Station via Interacting Multiple Model Filter in CDMA Environment
• Robust Relative Transfer Function Estimation for Dual Microphone-Based Generalized Sidelobe Canceller
• Optimal Gain Filter Design for Perceptual Acoustic Echo Suppressor

スポンサーリンク