A multi-modal virtual environment with text-independent real-time speaker identification.
Serhan DagtasMustafa SarimollaogluKamran IqbalPublished in: ISMSE (2004)
Keyphrases
- multi modal
- virtual environment
- speaker identification
- real time
- video search
- virtual reality
- real environment
- broadcast news
- speech recognition
- audio visual
- multiple modalities
- noisy environments
- gaussian mixture model
- feature extraction
- speech signal
- high dimensional
- text mining
- information retrieval
- vision system
- text documents
- feature selection
- semantic concepts