Speaker Identification by Combining Various Vocal Tract and Vocal Source Features.
Yuta KawakamiLongbiao WangAtsuhiko KaiSeiichi NakagawaPublished in: TSD (2014)
Keyphrases
- speech signal
- speaker identification
- vocal tract
- speech recognition
- low level
- feature extraction
- feature vectors
- automatic speech recognition
- noisy environments
- wavelet transform
- feature set
- speech synthesis
- linear prediction
- computer vision
- k means
- probabilistic neural network
- image acquisition
- gaussian mixture model
- machine learning
- non stationary
- image features