Automatic Speech Pronunciation Correction with Dynamic Frequency Warping-Based Spectral Conversion.
Nobukatsu HojoHirokazu KameokaKou TanakaTakuhiro KanekoPublished in: EUSIPCO (2018)
Keyphrases
- speech recognition
- spontaneous speech
- short time fourier transform
- cepstral coefficients
- spectral analysis
- automatic speech recognition
- speaker adaptation
- speech music discrimination
- spectral characteristics
- speaker independent
- spectral features
- text to speech
- linear prediction
- image warping
- speech synthesis
- speech recognizer
- frequency spectrum
- recognition engine
- human machine interaction
- speaker identification
- speech signal
- context sensitive
- dynamic environments