Single-Channel Multiple Regression for In-Car Speech Enhancement

スポンサーリンク

概要

• 論文の詳細を見る

• We address issues for improving hands-free speech enhancement and speech recognition performance in different car environments using a single distant microphone. This paper describes a new single-channel in-car speech enhancement method that estimates the log spectra of speech at a close-talking microphone based on the nonlinear regression of the log spectra of noisy signal captured by a distant microphone and the estimated noise. The proposed method provides significant overall quality improvements in our subjective evaluation on the regression-enhanced speech, and performed best in most objective measures. Based on our isolated word recognition experiments conducted under 15 real car environments, the proposed adaptive nonlinear regression approach shows an advantage in average relative word error rate (WER) reductions of 50.8% and 13.1%, respectively, compared to original noisy speech and ETSI advanced front-end (ETSI ES 202 050).

• 社団法人電子情報通信学会の論文
• 2006-03-01

著者

• TAKEDA Kazuya

  Nagoya University

• Takeda Kazuya

  Nagoya Univ.

• Takeda Kazuya

  Nagoya Univ. Nagoya‐shi Jpn

• Li Weifeng

  The Department Of Information Electronics Graduate School Of Engineering Nagoya University

• Takeda Kazuya

  The Department Of Media Science Graduate School Of Information Science Nagoya University

• Itou Katsunobu

  Faculty Of Computer And Information Sciences Hosei University

• ITAKURA Fumitada

  Graduate School of Information Engineering, Meijo University

• Itakura Fumitada

  The Faculty Of Science And Technology Meijo University

• ITAKURA Fumitada

  the Department of Information Engineering, Meijo University

• ITOU Katsunobu

  the Department of Media Science, Graduate School of Information Science, Nagoya University

• LI Weifeng

  the Faculty of Science and Technology, Meijo University

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
• CENSREC-1-C : An evaluation framework for voice activity detection under noisy environments
• Driver Identification Using Driving Behavior Signals(Human-computer Interaction)
• AURORA-2J: An Evaluation Framework for Japanese Noisy Speech Recognition(Speech Corpora and Related Topics, Corpus-Based Speech Technologies)
• 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)
• 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
• An Acoustically Oriented Vocal-Tract Model
• 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)
• Method for determining sound localization by auditory masking
• Acoustic Model Training Using Pseudo-Speaker Features Generated by MLLR Transformations for Robust Speaker-Independent Speech Recognition
• CENSREC-4: An evaluation framework for distant-talking speech recognition in reverberant environments
• A Graph-Based Spoken Dialog Strategy Utilizing Multiple Understanding Hypotheses
• 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