German text-to-audiovisual-speech by 3-d speaker cloning.
Sascha FagelGérard BaillyPublished in: AVSP (2008)
Keyphrases
- audio visual
- speech recognition
- text to speech
- automatic speech recognition
- speaker recognition
- speaker verification
- synthesized speech
- emotion recognition
- prosodic features
- multi modal
- text to speech synthesis
- speaker identification
- text recognition
- multi lingual
- visual information
- spontaneous speech
- conversational speech
- lexical features
- language generation
- automatic speech recognition systems
- text mining
- text input
- text documents
- text retrieval
- speech signal
- speaker dependent
- speech synthesis
- speaker diarization
- vocal tract
- english text
- spoken documents
- multimedia
- information retrieval
- gaussian mixture model
- text categorization
- text data
- natural language processing
- noisy environments
- speech sounds
- automatic transcription
- keywords