強健性語音辨識中基於小波轉換之分頻統計補償技術的研究 (A Study of Sub-band Feature Statistics Compensation Techniques Based on a Discrete Wavelet Transform for Robust Speech Recognition) [In Chinese].
Hao-Teng FanWen-Hsiang TuJeih-weih HungPublished in: ROCLING (2009)
Keyphrases
- discrete wavelet transform
- speech recognition
- subband
- wavelet coefficients
- wavelet domain
- multiresolution
- feature vectors
- high frequency
- noisy environments
- hidden markov models
- wavelet transform
- shift invariant
- low pass
- image fusion
- lifting scheme
- image compression
- language model
- pattern recognition
- speaker identification
- multiscale
- wavelet filters
- dual tree
- speech signal
- low frequency
- wavelet decomposition
- contourlet transform
- filter bank
- frequency domain
- high quality