An Audio System of Electronic Texts for the Visually Impaired and Perception of Different Speech Rates by the Blind and the Sighted.
Meelis MihklaIndrek HeinIndrek KiisselMargit OrusaarArtur RäppPublished in: Baltic HLT (2010)
Keyphrases
- audio stream
- audio visual
- broadcast news
- visually impaired users
- audio signals
- text to speech
- cepstral features
- digital audio
- emotion recognition
- multimodal interaction
- speaker identification
- speech music discrimination
- speech processing
- audio features
- prosodic features
- speech recognition
- audio recordings
- electronic documents
- audio video
- text input
- acoustic signals
- multi modal
- multi stream
- automatic transcription
- linear predictive coding
- signal processing
- multimedia
- spoken documents
- speech synthesis
- speech signal
- visual information
- digital video
- spontaneous speech
- visual perception
- natural language
- visual data
- spoken language
- human language
- speaker diarization
- multimodal interfaces
- audio signal
- automatic speech recognition
- emotional state
- natural language generation
- mel frequency cepstral coefficients
- visual speech
- speech corpus
- speaker verification