Deep Learning Based Multi-Channel Speaker Recognition in Noisy and Reverberant Environments.
Hassan TaherianZhong-Qiu WangDeLiang WangPublished in: INTERSPEECH (2019)
Keyphrases
- multi channel
- deep learning
- speaker recognition
- speech signal
- noisy environments
- speaker verification
- gaussian mixture model
- speaker identification
- speech recognition
- unsupervised learning
- vector quantization
- machine learning
- weakly supervised
- mental models
- probabilistic neural network
- non stationary
- learning algorithm
- neural network
- sound source
- reinforcement learning
- training data
- feature selection