Multiresolution CNN for reverberant speech recognition.
Sunchan ParkYongwon JeongHyung Soon KimPublished in: O-COCOSDA (2017)
Keyphrases
- speech recognition
- multiresolution
- speech signal
- automatic speech recognition
- hidden markov models
- speech processing
- pattern recognition
- language model
- wavelet transform
- speaker identification
- background noise
- speech recognizer
- noisy environments
- speaker recognition
- linear prediction
- image fusion
- subband
- wavelet decomposition
- speech recognition technology
- speech recognition systems
- speech synthesis
- speech understanding
- quadtree
- keyword spotting
- speech recognizers
- speaker dependent
- discrete wavelet transform
- speech enhancement
- wavelet coefficients
- speech retrieval
- broadcast news
- machine learning