A Review of Common Online Speaker Diarization Methods

TL;DR

This paper reviews online speaker diarization, discussing its history, taxonomy, datasets, methods, and challenges, emphasizing the need for low-latency speaker labeling in real-time audio processing.

Contribution

It provides a comprehensive overview of online speaker diarization methods, datasets, and challenges, highlighting areas for future research and development.

Findings

Summarizes the evolution of online speaker diarization techniques.

Identifies key datasets used for training and evaluation.

Outlines unresolved challenges in achieving low-latency diarization.

Abstract

Speaker diarization provides the answer to the question "who spoke when?" for an audio file. This information can be used to complete audio transcripts for further processing steps. Most speaker diarization systems assume that the audio file is available as a whole. However, there are scenarios in which the speaker labels are needed immediately after the arrival of an audio segment. Speaker diarization with a correspondingly low latency is referred to as online speaker diarization. This paper provides an overview. First the history of online speaker diarization is briefly presented. Next a taxonomy and datasets for training and evaluation are given. In the sections that follow, online diarization methods and systems are discussed in detail. This paper concludes with the presentation of challenges that still need to be solved by future research in the field of online speaker diarization.