Elastic spectral distortion for low resource speech recognition with deep neural networks.
Naoyuki KandaRyu TakedaYasunari ObuchiPublished in: ASRU (2013)
Keyphrases
- speech recognition
- neural network
- pattern recognition
- hidden markov models
- cepstral coefficients
- speaker adaptation
- language model
- automatic speech recognition
- speech synthesis
- speech signal
- speech recognizer
- speech processing
- speech recognition systems
- speech understanding
- speech recognition technology
- speaker identification
- isolated word
- keyword spotting
- speech recognition errors
- linear prediction
- spectral analysis
- vocal tract
- speaker diarization
- speaker independent
- noisy environments
- hyperspectral
- speech recognizers
- machine learning