SNR and sub-band SNR estimation based on Gaussian mixture modeling in the log power domain with application for speech enhancements (第6回音声言語シンポジウム)

スポンサーリンク

概要

• 論文の詳細を見る

• This work presents a flexible blind SNR estimation method based on Gaussian mixture modeling (GMM) in the log-power domain. Considering the local noise and noisy speech powers as two log-normal distributed random variables, their distribution parameters are estimated via the EM algorithm and used to derive the segmental SNR, which is defined as the expectation distance between two subspace distributions. A compensation mode for the estimation under low SNR conditions ais also proposed. The experimental resuits, evaluated on the AURORA2 database, show the more consistency of proposed estimation method in both the noise conditions, compared to the conventional methods. The second application presented in this work is sub-band SNRs estimations for speech enhancement systems. Here the GMM is applied to each frequency bin, and then two methods of the sub-band SNRs estimation are proposed by using the maximum a posterior (MAP) decomposition and cumulative distribution function (CDF) equalization. Furthermore, the sub-band SNR is used for the Wiener filtering systems. The evaluation experiments demonstrate the improvements of the proposed speech enhancement method in both segmental SNR and ASR performances.

• 一般社団法人情報処理学会の論文
• 2004-12-20

著者

• TAKEDA Kazuya

  Nagoya University

• Takeda K

  Nagoya Univ. Nagoya Jpn

• Takeda Kazuya

  Graduate School Of Information Science Nagoya University

• Takeda Kazuya

  Nagoya Univ. Nagoya‐shi Jpn

• Huy Dat

  Institute For Infocomm Research

• ITAKURA Fumitada

  Graduate School of Information Engineering, Meijo University

• HUY DAT

  Graduate School of Information Science, Nagoya University

• FUJIMURA Hiroshi

  Graduate School of Information Science, Nagoya University

• Itakura Fumitada

  The Faculty Of Science And Technology Meijo University

• Fujimura Hiroshi

  Department Of Media Science Graduate School Of Information Science Nagoya University

• Itakura Fumitada

  Graduate School Of Information Engineering Meijo University

• Takeda Kazuya

  Graduate School Of Information Science At Nagoya University

• Itakura Fumitada

  Graduate School of Engineering, Nagoya University:Center for Integrated Acoustic Information Research, Nagoya University

• TAKEDA Kazuya

  Graduate School of Engineering, Nagoya University

• Itakura Fumitada

  Graduate School of Engineering, Nagoya University/CIAIR

関連論文

• Acoustic Feature Transformation Combining Average and Maximum Classification Error Minimization Criteria
• Acoustic Feature Transformation Based on Discriminant Analysis Preserving Local Structure for Speech Recognition
• AN INTEGRATED AUDIO-VISUAL VIEWER FOR A LARGE SCALE MULTIPOINT CAMERAS AND MICROPHONES(International Workshop on Advanced Image Technology 2007)
• CENSREC-1-C : An evaluation framework for voice activity detection under noisy environments
• Driver Identification Using Driving Behavior Signals(Human-computer Interaction)
• AN INTEGRATED AUDIO-VISUAL VIEWER FOR A LARGE SCALE MULTIPOINT CAMERAS AND MICROPHONES
• G_007 Arbitrary Listening-point Generation Using Acoustic Transfer Function Interpolation in A Large Microphone Array
• THE SUB-BAND SOUND WAVE RAY-SPACE REPRESENTATION(International Workshop on Advanced Image Technology 2006)
• A-16-24 3D Sound Wave Field Representation Based on Ray-Space Method(A-16. マルチメディア・仮想環境基礎, 基礎・境界)
• AURORA-2J: An Evaluation Framework for Japanese Noisy Speech Recognition(Speech Corpora and Related Topics, Corpus-Based Speech Technologies)
• Selective Listening Point Audio Based on Blind Signal Separation and Stereophonic Technology
• Head-Related Transfer Function measurement in sagittal and frontal coordinates
• CENSREC-3: An Evaluation Framework for Japanese Speech Recognition in Real Car-Driving Environments(Speech and Hearing)
• Evaluation of HRTFs estimated using physical features
• Multiple Regression of Log Spectra for In-Car Speech Recognition Using Multiple Distributed Microphones(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)
• Evaluation of Combinational Use of Discriminant Analysis-Based Acoustic Feature Transformation and Discriminative Training
• Acoustic Feature Transformation Based on Discriminant Analysis Preserving Local Structure for Speech Recognition
• Gamma Modeling of Speech Power and Its On-Line Estimation for Statistical Speech Enhancement(Speech Enhancement, Statistical Modeling for Speech Processing)
• Multichannel Speech Enhancement Based on Generalized Gamma Prior Distribution with Its Online Adaptive Estimation
• SNR and sub-band SNR estimation based on Gaussian mixture modeling in the log power domain with application for speech enhancements (第6回音声言語シンポジウム)
• SNR and sub-band SNR estimation based on Gaussian mixture modeling in the log power domain with application for speech enhancements (第6回音声言語シンポジウム)
• SNR and sub-band SNR estimation based on Gaussian mixture modeling in the log power domain with application for speech enhancements (第6回音声言語シンポジウム)
• Acoustic Feature Transformation Combining Average and Maximum Classification Error Minimization Criteria
• Driver's irritation detection using speech recognition results (音声・第10回音声言語シンポジウム)
• Driver's irritation detection using speech recognition results (音声言語情報処理)
• Driver's irritation detection using speech recognition results (言語理解とコミュニケーション・第10回音声言語シンポジウム)
• サブバンドに含まれる周波数成分の瞬時周波数に基づく推定
• Predicting the Degradation of Speech Recognition Performance from Sub-band Dynamic Ranges (特集 音声言語情報処理とその応用)
• A model of perceptual distance for group delays based on ellipsoidal mapping
• The effect of group delay spectrum on timbre
• Direction of Arrival Estimation Using Nonlinear Microphone Array
• Speech Enhancement Using Nonlinear Microphone Array Based on Noise Adaptive Complementary Beamforming
• Speech Enhancement Using Nonlinear Microphone Array Based on Complementary Beamforming (Special Section on Digital Signal Processing)
• Noise Robust Speech Recognition Using Subband-Crosscorrelation Analysis
• An Acoustically Oriented Vocal-Tract Model
• Comparison of acoustic measures for evaluating speech recognition performance in an automobile
• Estimation of speaker and listener positions in a car using binaural signals
• Sound localization under conditions of covered ears on the horizontal plane
• Single-Channel Multiple Regression for In-Car Speech Enhancement
• Adaptive Nonlinear Regression Using Multiple Distributed Microphones for In-Car Speech Recognition(Speech Enhancement, Multi-channel Acoustic Signal Processing)
• Speech Recognition Using Finger Tapping Timings(Speech and Hearing)
• CIAIR In-Car Speech Corpus : Influence of Driving Status(Corpus-Based Speech Technologies)
• Construction and Evaluation of a Large In-Car Speech Corpus(Speech Corpora and Related Topics, Corpus-Based Speech Technologies)
• Blind Source Separation Using Dodecahedral Microphone Array under Reverberant Conditions
• FOREWORD : Spercial Section on Robust Speech Processing in Realistic Environments
• Method for determining sound localization by auditory masking
• Classification of speech under stress by physical modeling
• Classification of speech under stress using physical features based on two-mass model
• Acoustic Model Training Using Pseudo-Speaker Features Generated by MLLR Transformations for Robust Speaker-Independent Speech Recognition

もっと見る 閉じる

スポンサーリンク