A Study Of Semi-supervised Speaker Diarization System Using Gan Mixture Model

Abstract

We propose a new speaker diarization system based on a recently introduced unsupervised clustering technique namely, generative adversarial network mixture model (GANMM). The proposed system uses x-vectors as front-end representation. Spectral embedding is used for dimensionality reduction followed by k-means initialization during GANMM pre-training. GANMM performs unsupervised speaker clustering by efficiently capturing complex data distributions. Experimental results on the AMI meeting corpus show that the proposed semi-supervised diarization system matches or exceeds the performance of competitive baselines. On an evaluation set containing fifty sessions with varying durations, the best achieved average diarization error rate (DER) is 17.11%, a relative improvement of 33% over the information bottleneck baseline and comparable to xvector baseline.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keypal2019a

Related papers

• Meta-learning With Latent Space Clustering In Generative Adversarial Network For Speaker Diarization (2020)9.03
• Simultaneous Diarization And Separation Of Meetings Through The Integration Of Statistical Mixture Models (2024)0.00
• Robust Speaker Clustering Using Mixtures Of Von Mises-fisher Distributions For Naturalistic Audio Streams (2018)4.52
• Multi-class Spectral Clustering With Overlaps For Speaker Diarization (2020)10.35
• Enhancements For Audio-only Diarization Systems (2019)0.00
• Towards Unsupervised Speaker Diarization System For Multilingual Telephone Calls Using Pre-trained Whisper Model And Mixture Of Sparse Autoencoders (2024)2.26
• Tight Integration Of Neural- And Clustering-based Diarization Through Deep Unfolding Of Infinite Gaussian Mixture Model (2022)8.60
• End-to-end Supervised Hierarchical Graph Clustering For Speaker Diarization (2024)5.24