An i-vector Extractor Suitable for Speaker Recognition with both Microphone and Telephone Speech.
Mohammed SenoussaouiPatrick KennyNajim DehakPierre DumouchelPublished in: Odyssey (2010)
Keyphrases
- speaker recognition
- gaussian mixture model
- vector quantization
- speaker verification
- speech signal
- speaker identification
- probabilistic neural network
- speech recognition
- automatic speech recognition
- feature vectors
- speaker diarization
- noisy environments
- pattern recognition
- neural network
- audio visual
- sound source
- mel frequency cepstral coefficients
- gaussian process regression
- mixture model
- semi supervised
- feature space
- multiscale