LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarization
This addresses speaker diarization for audio analysis, offering a significant performance improvement over existing methods.
The paper tackles speaker diarization by proposing a supervised Bi-LSTM method to measure similarity between speech segments, combined with spectral clustering, achieving a diarization error rate of 6.63% on the NIST SRE 2000 CALLHOME database and outperforming state-of-the-art methods.
More and more neural network approaches have achieved considerable improvement upon submodules of speaker diarization system, including speaker change detection and segment-wise speaker embedding extraction. Still, in the clustering stage, traditional algorithms like probabilistic linear discriminant analysis (PLDA) are widely used for scoring the similarity between two speech segments. In this paper, we propose a supervised method to measure the similarity matrix between all segments of an audio recording with sequential bidirectional long short-term memory networks (Bi-LSTM). Spectral clustering is applied on top of the similarity matrix to further improve the performance. Experimental results show that our system significantly outperforms the state-of-the-art methods and achieves a diarization error rate of 6.63% on the NIST SRE 2000 CALLHOME database.