Detecting child speaker based on auditory feature vectors for VTL estimation.
Ryuichi NisimuraShoko MiyamoriErika OkamotoHideki KawaharaToshio IrinoPublished in: APSIPA (2012)
Keyphrases
- feature vectors
- feature space
- audio visual
- support vector machine
- signal processing
- information processing
- rotation invariant
- euclidean distance
- face images
- automatic speech recognition
- estimation process
- robust estimation
- feature extraction
- accurate estimation
- pattern recognition
- visual information
- automatic detection
- speaker recognition
- estimation accuracy
- gaussian mixture model
- kullback leibler distance
- texture features
- machine learning
- speech recognition
- image processing