LSTM Neural Network for Speaker Change Detection in Telephone Conversations

摘要

In this paper, we analyze an approach to speaker change detection in telephone conversations based on recurrent Long Short-Term Memory Neural Networks. We compare this approach to speaker change detection via Convolutional Neural Networks. We show that by finetun-ing the architecture and using suitable input data in the form of spectrograms, we obtain better results relatively by 2%. We have discovered that a smaller architecture performs better on unseen data. Also, we found out that using stateful LSTM layers that try to remember whole conversations is much worse than using recurrent networks that memorize only small sequences of speech.