Convolutional Neural Networks for Classification of Voice Qualities from Speech and Neck Surface Accelerometer Signals.
Sudarsana Reddy KadiriFarhad JavanmardiPaavo AlkuPublished in: INTERSPEECH (2022)
Keyphrases
- fundamental frequency
- text to speech
- speech signal
- voice activity detection
- speech recognition
- emotion recognition
- acoustic signals
- speech quality
- speech recognition errors
- noisy environments
- signal processing
- speech synthesis
- audio signals
- skin surface
- three dimensional
- spectral analysis
- gesture recognition
- surface reconstruction
- automatic speech recognition
- emg signals
- acoustic signal
- d objects
- spoken language
- network architecture
- spectral features
- audio visual
- range data
- activity recognition
- range images
- synthesized speech
- text to speech synthesis