Noise Robust Feature Scheme for Automatic Speech Recognition Based on Auditory Perceptual Mechanisms
スポンサーリンク
概要
- 論文の詳細を見る
Mel Frequency Cepstral Coefficients (MFCC) are the most popular acoustic features used in automatic speech recognition (ASR), mainly because the coefficients capture the most useful information of the speech and fit well with the assumptions used in hidden Markov models. As is well known, MFCCs already employ several principles which have known counterparts in the peripheral properties of human hearing: decoupling across frequency, mel-warping of the frequency axis, log-compression of energy, etc. It is natural to introduce more mechanisms in the auditory periphery to improve the noise robustness of MFCC. In this paper, a k-nearest neighbors based frequency masking filter is proposed to reduce the audibility of spectra valleys which are sensitive to noise. Besides, Moore and Glasberg's critical band equivalent rectangular bandwidth (ERB) expression is utilized to determine the filter bandwidth. Furthermore, a new bandpass infinite impulse response (IIR) filter is proposed to imitate the temporal masking phenomenon of the human auditory system. These three auditory perceptual mechanisms are combined with the standard MFCC algorithm in order to investigate their effects on ASR performance, and a revised MFCC extraction scheme is presented. Recognition performances with the standard MFCC, RASTA perceptual linear prediction (RASTA-PLP) and the proposed feature extraction scheme are evaluated on a medium-vocabulary isolated-word recognition task and a more complex large vocabulary continuous speech recognition (LVCSR) task. Experimental results show that consistent robustness against background noise is achieved on these two tasks, and the proposed method outperforms both the standard MFCC and RASTA-PLP.
- 2012-06-01
著者
-
Yan Yonghong
Key Laboratory Of Speech Acoustics And Content Understanding Chinese Academy Of Sciences
-
ZHAO Qingwei
Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences
-
CAI Shang
Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences
-
PAN Jielin
Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences
-
XIAO Yeming
Key Laboratory of Speech Acoustics and Content Understanding, Chinese Academy of Sciences
-
YAN Yonghong
Key Laboratory of Speech Acoustics and Content Understanding
-
ZHAO Qingwei
Key Laboratory of Speech Acoustics and Content Understanding
関連論文
- Factor Analysis of Neighborhood-Preserving Embedding for Speaker Verification
- Logarithmic Adaptive Quantization Projection for Audio Watermarking
- Noise Robust Feature Scheme for Automatic Speech Recognition Based on Auditory Perceptual Mechanisms
- A Forced Alignment Based Approach for English Passage Reading Assessment
- A Novel Discriminative Method for Pronunciation Quality Assessment
- Discriminative Approach to Build Hybrid Vocabulary for Conversational Telephone Speech Recognition of Agglutinative Languages
- Logarithmic Adaptive Quantization Projection for Audio Watermarking
- Smoothing Method for Improved Minimum Phone Error Linear Regression