Intelligibility of audio-visually desynchronised speech: asymmetrical effect of phoneme position.
Paula M. T. SmeeleAnne C. SittigVincent J. van HeuvenPublished in: ICSLP (1992)
Keyphrases
- speech recognition
- speaker identification
- speech processing
- speech synthesis
- automatic speech recognition
- prosodic features
- broadcast news
- speech signal
- audio visual
- speaker dependent
- hidden markov models
- language model
- audio stream
- text to speech
- audio signals
- visual speech
- speech recognizer
- noisy environments
- pattern recognition
- cepstral features
- multimedia
- emotion recognition
- speaker recognition
- speech recognition systems
- audio recordings
- signal processing
- phoneme recognition
- automatic speech recognition systems
- voice activity detection
- speaker diarization
- automatic transcription
- spontaneous speech
- speech sounds
- speech music discrimination
- digital audio
- vocal tract
- multi stream
- acoustic features
- position information
- digital video