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.

Accepted for INTERSPEECH 2019

Cited by in corpus (20)

• Auto-Tuning Spectral Clustering for Speaker Diarization Using Normalized Maximum Eigengap
• Discriminative Neural Clustering for Speaker Diarisation
• The VoxCeleb Speaker Recognition Challenge: A Retrospective
• The DKU-DukeECE-Lenovo System for the Diarization Task of the 2021 VoxCeleb Speaker Recognition Challenge
• Self-supervised Representation Learning With Path Integral Clustering For Speaker Diarization
• Combination of Deep Speaker Embeddings for Diarisation
• Channel adversarial training for speaker verification and diarization
• Novel Architectures for Unsupervised Information Bottleneck based Speaker Diarization of Meetings
• Speaker Recognition Based on Deep Learning: An Overview
• DIHARD II is Still Hard: Experimental Results and Discussions from the DKU-LENOVO Team
• TSUP Speaker Diarization System for Conversational Short-phrase Speaker Diarization Challenge
• Community Detection Graph Convolutional Network for Overlap-Aware Speaker Diarization
• A Thousand Words are Worth More Than One Recording: NLP Based Speaker Change Point Detection
• Self-Tuning Spectral Clustering for Speaker Diarization
• Learning deep representations by multilayer bootstrap networks for speaker diarization
• Understand customer reviews with less data and in short time: pretrained language representation and active learning
• End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection
• Semi-Supervised Training with Pseudo-Labeling for End-to-End Neural Diarization
• Speaker diarization with session-level speaker embedding refinement using graph neural networks
• DNN Speaker Tracking with Embeddings