The SRI International STAR-LAB System Description for IberSPEECH-RTVE 2018 Speaker Diarization Challenge

Abstract

This document describes the submissions of STAR-LAB (the Speech Technology and Research Laboratory at SRI International) to the open-set condition of the IberSPEECH-RTVE 2018 Speaker Diarization Challenge. The core components of the submissions included noise-robust speech activity detection, speaker embeddings for initializing diarization with domain adaptation, and Variational Bayes (VB) diarization using a DNN bottleneck i-vector subspaces.