Voice activity detection and speaker localization using audiovisual cues.
Dante A. BlauthVicente P. MinottoCláudio Rosito JungBowon LeeTon KalkerPublished in: Pattern Recognit. Lett. (2012)
Keyphrases
- voice activity detection
- speech recognition
- audio visual
- noisy environments
- speaker verification
- prosodic features
- speaker identification
- multi modal
- speaker recognition
- visual information
- emotion recognition
- speech signal
- automatic speech recognition
- video retrieval
- multimedia content
- prior knowledge
- pattern recognition
- language model
- localization error
- accurate localization
- machine learning
- position information
- unsupervised learning
- hidden markov models
- acoustic features
- optic disc
- localization method