English

A study of semi-supervised speaker diarization system using gan mixture model

Audio and Speech Processing 2019-10-28 v1 Sound

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.

Keywords

Cite

@article{arxiv.1910.11416,
  title  = {A study of semi-supervised speaker diarization system using gan mixture model},
  author = {Monisankha Pal and Manoj Kumar and Raghuveer Peri and Shrikanth Narayanan},
  journal= {arXiv preprint arXiv:1910.11416},
  year   = {2019}
}

Comments

Submitted to ICASSP 2020

R2 v1 2026-06-23T11:54:18.474Z