Look, Listen and Learn - A Multimodal LSTM for Speaker Identification.

Jimmy S. J. Ren Yongtao Hu Yu-Wing Tai Chuan Wang Li Xu Wenxiu Sun Qiong Yan

Published in: CoRR (2016)

Keyphrases

speaker identification
gaussian mixture model
noisy environments
multi modal
speech recognition
broadcast news
speaker recognition
speech signal
feature extraction
multimedia
recurrent neural networks
video search