Speaker Diarization using Deep Recurrent Convolutional Neural Networks for Speaker Embeddings
This work addresses speaker diarization for broadcast material, offering a significant performance improvement over traditional methods.
The paper tackles speaker diarization by proposing a deep learning method that learns speaker embeddings directly from spectrograms, achieving a reduction in diarization error rate by over 30% compared to baselines.
In this paper we propose a new method of speaker diarization that employs a deep learning architecture to learn speaker embeddings. In contrast to the traditional approaches that build their speaker embeddings using manually hand-crafted spectral features, we propose to train for this purpose a recurrent convolutional neural network applied directly on magnitude spectrograms. To compare our approach with the state of the art, we collect and release for the public an additional dataset of over 6 hours of fully annotated broadcast material. The results of our evaluation on the new dataset and three other benchmark datasets show that our proposed method significantly outperforms the competitors and reduces diarization error rate by a large margin of over 30% with respect to the baseline.