A Textless Metric for Speech-to-Speech Comparison.
Laurent BesacierSwen RibeiroOlivier GalibertIoan CalapodescuPublished in: CoRR (2022)
Keyphrases
- speech recognition
- speech signal
- automatic speech recognition
- endpoint detection
- speech synthesis
- spoken language
- text to speech
- natural language
- audio visual
- multi stream
- multiscale
- automatic speech recognition systems
- spontaneous speech
- speaker recognition
- emotion recognition
- dialogue system
- speech processing
- human communication
- broadcast news
- recognition engine
- mobile robot
- artificial intelligence