Combination of bottleneck feature extraction and dereverberation for distant-talking speech recognition.
Bo RenLongbiao WangLiang LuYuma UedaAtsuhiko KaiPublished in: Multim. Tools Appl. (2016)
Keyphrases
- speech recognition
- feature extraction
- speaker identification
- hidden markov models
- pattern recognition
- cepstral coefficients
- language model
- speech recognizer
- speech synthesis
- speech signal
- automatic speech recognition
- speech understanding
- speech processing
- speech recognition technology
- noisy environments
- feature selection
- principal component analysis
- wavelet transform
- speech recognition systems
- speaker independent
- image processing
- image classification
- feature space
- speaker dependent
- speech retrieval
- speech recognizers
- feature vectors
- face recognition
- mel frequency cepstral coefficients
- speaker adaptation
- speech recognition errors
- computer vision