A comparison of the performance of "normal" and "whispered" speech with simple time encoded digital speech (TES) direct voice input (DVI) systems in a tactical military environment.
R. D. HughesR. A. KingPublished in: EUROSPEECH (1989)
Keyphrases
- endpoint detection
- text to speech
- speech recognition
- text input
- automatic speech recognition systems
- emotion recognition
- noisy environments
- speech synthesis
- audio visual
- speech recognition errors
- speech quality
- management system
- speech signal
- automatic speech recognition
- voice activity detection
- speech recognition systems
- neural network
- computer systems
- mobile robot
- operating environment
- recognition engine
- command and control
- fundamental frequency
- prosodic features
- spoken dialogue systems
- speaker identification
- automatic transcription
- broadcast news
- complex systems
- distributed systems