Noise robust speaker identification by dividing MFCC.
Kizuki MatsumotoNoboru HayasakaYouji IiguniPublished in: ISCCSP (2014)
Keyphrases
- speaker identification
- noisy environments
- speech recognition
- noise reduction
- speech signal
- speaker recognition
- mel frequency cepstral coefficients
- feature transformation
- gaussian mixture model
- speaker verification
- probabilistic neural network
- feature extraction
- broadcast news
- audio signal
- automatic speech recognition
- information retrieval
- image classification
- hidden markov models
- pattern recognition
- computer vision