Speech Enhancement Based on Adaptive Noise Power Estimation Using Spectral Difference
スポンサーリンク
概要
- 論文の詳細を見る
In this paper, we propose a spectral difference approach for noise power estimation in speech enhancement. The noise power estimate is given by recursively averaging past spectral power values using a smoothing parameter based on the current observation. The smoothing parameter in time and frequency is adjusted by the spectral difference between consecutive frames that can efficiently characterize noise variation. Specifically, we propose an effective technique based on a sigmoid-type function in order to adaptively determine the smoothing parameter based on the spectral difference. Compared to a conventional method, the proposed noise estimate is computationally efficient and able to effectively follow noise changes under various noise conditions.
- 2011-10-01
著者
-
Chang Joon-hyuk
School Of Electronic And Electrical Engineering Inha University
-
Kim Dong
School Of Electrical And Electronic Engineering At Yonsei University
-
Choi Jae-hun
School Of Electronic Engineering Hanyang University
-
Chang Joon-hyuk
School Of Electronic Engineering Hanyang University
-
KIM Suhyun
Image Media Research Center, KIST
-
Kim Suhyun
Image Media Research Center Kist
-
CHANG Joon-Hyuk
School of Electronic Engineering, Hanyang University
-
KIM Dong
School of Electronic Engineering, Chonnam National University
-
Kim Dong
School of Clinical Sciences, University of Bristol
関連論文
- A Synchronization and Cell Searching Technique Using Pilot Tones for OFDM Cellular Systems(Wireless Communication Technologies)
- Joint subchannel matching and power allocation for the MIMO broadcast relay channel
- Structural and electrical properties of Mg_2TiO_4
- Pre-Processed Recursive Lattice Reduction for Complexity Reduction in Spatially and Temporally Correlated MIMO Channels
- Calibration, Prediction and Process Monitoring Model Based on Factor Analysis for Incomplete Process Data
- Efficient Implementation of Voiced/Unvoiced Sounds Classification Based on GMM for SMV Codec
- A Closed Form Solution for the Sum Rate of Multiple Random Beamforming
- Downlink Beamforming Throughput Maximization for Multi-Cell Environment in the Presence of the Channel Uncertainty
- Analytic Model for the Gate Current of MODFET's with and without Photonic Control
- Analytic Model for the Gate Current of MODFET's with and without Photonic Control
- Row-by-Row Dynamic Source-Line Voltage Control (RRDSV) Scheme for Two Orders of Magnitude Leakage Current Reduction of Sub-1-V-V_SRAM's(Electronic Circuits)
- Improved Global Soft Decision Using Smoothed Global Likelihood Ratio for Speech Enhancement(Multimedia Systems for Communications)
- AC Stress-Induced Degradation of Amorphous InGaZnO Thin Film Transistor Inverter
- On the Performance of the Two-Cell Cooperative Single User (CSU) MIMO System with Hybrid Feedback
- Speech Reinforcement Based on Soft Decision under Far-End Noise Environments
- A Support Vector Machine-Based Gender Identification Using Speech Signal
- Study on the effects of Zr-incorporated InZnO thin-film transistors using a solution process
- Frame Splitting Scheme for Error-Robust Audio Streaming over Packet-Switching Networks
- Acoustic Environment Classification Based on SMV Speech Codec Parameters for Context-Aware Mobile Phone
- Weighted Sum-MSE Minimization for the Multiuser MIMO Relay System
- Improvement of SVM-Based Speech/Music Classification Using Adaptive Kernel Technique
- Speech Enhancement Based on Data-Driven Residual Gain Estimation
- Speech Enhancement Based on Adaptive Noise Power Estimation Using Spectral Difference
- Origin of Device Performance Degradation in InGaZnO Thin-Film Transistors after Crystallization
- A Statistical Model-Based Speech Enhancement Using Acoustic Noise Classification for Robust Speech Communication
- Approaches to Decreasing the Processing Temperature for a Solution-Processed InZnO Thin-Film Transistors
- Involvement of histaminergic system in the anxiolytic-like activities of Morus alba L. leaves in mice