加成性雜訊環境下運用特徵參數統計補償法於強健性語音辨識 (Feature Statistics Compensation for Robust Speech Recognition in Additive Noise Environments) [In Chinese].
Tsung-hsueh HsiehJeih-Weih HungPublished in: ROCLING (2007)
Keyphrases
- speech recognition
- additive noise
- speech signal
- noisy environments
- speech synthesis
- automatic speech recognition
- cepstral coefficients
- hidden markov models
- language model
- noisy images
- speaker identification
- speech recognition systems
- spatial domain
- speech processing
- speech recognizer
- background noise
- vocal tract
- speech recognition technology
- maximum likelihood
- pattern recognition
- point spread function
- speech enhancement
- linear prediction
- random variables
- non stationary
- feature vectors
- image segmentation
- signal to noise ratio
- speaker independent
- wavelet transform
- denoising
- principal component analysis
- edge detection
- graphical models
- wiener filter