Speaker identification from emotional and noisy speech using learned voice segregation and speech VGG.
Shibani HamsaIsmail ShahinYoussef IraqiErnesto DamianiAli Bou NassifNaoufel WerghiPublished in: Expert Syst. Appl. (2023)
Keyphrases
- speaker identification
- noisy speech
- speech recognition
- mel frequency cepstral coefficients
- speech signal
- noisy environments
- speech enhancement
- automatic speech recognition systems
- speaker recognition
- speech synthesis
- probabilistic neural network
- language identification
- gaussian mixture model
- hidden markov models
- emotion recognition
- automatic speech recognition
- vocal tract
- broadcast news
- non stationary
- language model
- background noise
- speaker verification
- feature extraction
- machine learning
- neural network
- linear prediction
- pattern recognition
- text to speech
- speaker diarization
- noise reduction