Convolutional Neural Networks-based continuous speech recognition using raw speech signal.
Dimitri PalazMathew Magimai-DossRonan CollobertPublished in: ICASSP (2015)
Keyphrases
- speech signal
- convolutional neural networks
- speech recognition
- automatic speech recognition
- convolutional network
- non stationary
- speaker identification
- vocal tract
- linear prediction
- spectral analysis
- background noise
- hidden markov models
- noisy environments
- automatic speech recognition systems
- speech enhancement
- acoustic features
- fundamental frequency
- high level
- sound source
- speaker recognition
- wavelet transform
- pattern recognition
- computer vision