The Second DISPLACE Challenge : DIarization of SPeaker and LAnguage in Conversational Environments

TL;DR

The DISPLACE 2024 challenge advances speaker and language diarization in multilingual conversational speech, introducing automatic speech recognition and providing a large, diverse dataset to benchmark state-of-the-art systems.

Contribution

This paper presents the second DISPLACE challenge with new ASR tasks, a comprehensive multilingual dataset, and baseline systems to foster progress in speaker and language diarization.

Findings

Baseline models show improved performance over DISPLACE-2023

Introduction of ASR task expands the challenge scope

Large dataset enables robust benchmarking

Abstract

The DIarization of SPeaker and LAnguage in Conversational Environments (DISPLACE) 2024 challenge is the second in the series of DISPLACE challenges, which involves tasks of speaker diarization (SD) and language diarization (LD) on a challenging multilingual conversational speech dataset. In the DISPLACE 2024 challenge, we also introduced the task of automatic speech recognition (ASR) on this dataset. The dataset containing 158 hours of speech, consisting of both supervised and unsupervised mono-channel far-field recordings, was released for LD and SD tracks. Further, 12 hours of close-field mono-channel recordings were provided for the ASR track conducted on 5 Indian languages. The details of the dataset, baseline systems and the leader board results are highlighted in this paper. We have also compared our baseline models and the team's performances on evaluation data of DISPLACE-2023 to emphasize the advancements made in this second version of the challenge.