Unsupervised deep feature embeddings for speaker diarization

Speaker diarization aims to determine "who spoke when?" from multispeaker recording environments. In this paper, we propose to learn a set of high-level feature representations, referred to as feature embeddings, from an unsupervised deep architecture for speaker diarization. These sets of embeddings are learned through a deep autoencoder model when trained on mel-frequency cepstral coefficients (MFCCs) of input speech frames. Learned embeddings are then used in Gaussian mixture model based hierarchical clustering for diarization. The results show that these unsupervised embeddings are better compared to MFCCs in reducing the diarization error rate. Experiments conducted on the popular subset of the AMI meeting corpus consisting of 5.4 h of recordings show that the new embeddings decrease the average diarization error rate by 2.96%. However, for individual recordings, maximum improvement of 8.05% is acquired.