Skip to Main content Skip to Navigation
Conference papers

LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarization

Abstract : 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.
Complete list of metadatas
Contributor : Limsi Publications <>
Submitted on : Friday, July 19, 2019 - 2:32:56 PM
Last modification on : Monday, February 10, 2020 - 6:14:09 PM


  • HAL Id : hal-02189393, version 1


Qingjian Lin, Ruiqing Yin, Ming Li, Hervé Bredin, Claude Barras. LSTM based Similarity Measurement with Spectral Clustering for Speaker Diarization. Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria. ⟨hal-02189393⟩



Record views