Handling disynchronization phenomena with HMM in connected speech.
Pierre JourlinPublished in: EUSIPCO (1996)
Keyphrases
- speech recognition
- hidden markov models
- speech signal
- multi stream
- automatic speech recognition systems
- automatic speech recognition
- speech synthesis
- recognition engine
- phoneme recognition
- keyword spotting
- speech recognizer
- speaker independent
- audio visual
- speaker identification
- speaker adaptation
- vocal tract
- speech processing
- linear prediction
- visual speech
- noisy speech
- pattern recognition
- broadcast news
- gesture recognition
- connected components
- language model
- forward backward
- multimodal interfaces
- text to speech
- speaker recognition
- noisy environments
- speech recognition systems
- dialogue system
- speaker dependent
- endpoint detection
- text to speech synthesis
- information retrieval