分頻式調變頻譜分解於強健性語音辨識 (Sub-band modulation spectrum factorization in robust speech recognition) [In Chinese].
Hao-Teng FanYi-zhang CaiJeih-weih HungPublished in: ROCLING (2013)
Keyphrases
- speech recognition
- subband
- noisy environments
- speech synthesis
- speech processing
- hidden markov models
- speech recognition technology
- speech signal
- language model
- multiresolution
- automatic speech recognition
- wavelet decomposition
- wavelet transform
- speech recognizer
- wavelet coefficients
- pattern recognition
- discrete wavelet transform
- low pass
- low frequency
- frequency domain
- image compression
- feature vectors
- filter bank
- high frequency
- speaker dependent
- speaker identification
- image data
- speech recognition systems
- speaker independent
- wavelet domain
- frequency band
- bit rate
- image coding
- power spectrum