A Robust Room Inverse Filtering Algorithm for Speech Dereverberation Based on a Kurtosis Maximization

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, we propose a robust room inverse filtering algorithm for speech dereverberation based on a kurtosis maximization. The proposed algorithm utilizes a new normalized kurtosis function that nonlinearly maps the input kurtosis onto a finite range from zero to one, which results in a kurtosis warping. Due to the kurtosis warping, the proposed algorithm provides more stable convergence and, in turn, better performance than the conventional algorithm. Experimental results are presented to confirm the robustness of the proposed algorithm.

• （社）電子情報通信学会の論文
• 2010-05-01

著者

• Youn Dae-hee

  Yonsei Univ. Biometrics Engineering Research Center

• PARK Young-Cheol

  Yonsei University

• JEONG Jae-woong

  Yonsei Univ.

• LEE Seok-Pil

  Korea Electronics Technology Institute

• Park Young-cheol

  Yonsei Univ.

• YOUN Dae-hee

  Yonsei Univ.

関連論文

• Efficient FFT Algorithm for Psychoacoustic Model of the MPEG-4 AAC
• A GMM-Based Feature Selection Algorithm for Multi-Class Classification
• Design of Time-Varying Reverberators for Low Memory Applications
• A Robust Room Inverse Filtering Algorithm for Speech Dereverberation Based on a Kurtosis Maximization
• 韓国における新しいデジタル放送サービスの開発と規状(海外の最新動向,デジタル放送の新展開)
• Efficient Windowing Scheme for MDCT-Based TCX in AMR-WB+
• LP/WLP Hybrid Scheme for Quality Improvement of TCX Coders Operating at Low Bit Rates

スポンサーリンク