Text-Independent Speaker Verification from Mixed Speech of Multiple Speakers via Using Pole Distribution of Speech Signals.
Toshiki TagomoriKazuya MatsuoShuichi KurogiPublished in: ICONIP (6) (2018)
Keyphrases
- speech signal
- noisy environments
- speaker verification
- speech recognition
- speaker recognition
- automatic speech recognition
- speech enhancement
- speaker identification
- acoustic features
- vocal tract
- hidden markov models
- linear prediction
- mel frequency cepstral coefficients
- noise reduction
- language identification
- prosodic features
- automatic speech recognition systems
- non stationary
- text mining
- formant frequencies
- language model
- information retrieval
- speech synthesis
- speech quality
- noisy speech
- multilayer perceptron
- neural network
- spontaneous speech
- fundamental frequency
- pattern recognition
- speech sounds