From visible speech to voiceprints - blessing and curse of sound spectrography.
Angelika BraunPublished in: HSCR (2017)
Keyphrases
- speech recognition
- automatic speech recognition systems
- high dimensional
- audio visual
- speech signal
- acoustic features
- spoken language
- high dimensional data
- automatic speech recognition
- endpoint detection
- speaker recognition
- information systems
- fundamental frequency
- speech recognizer
- emotion recognition
- dimension reduction
- spoken dialogue systems
- text to speech
- linear prediction
- spontaneous speech
- multi modal
- text to speech synthesis
- real time