AP19-OLR Challenge: Three Tasks and Their Baselines

TL;DR

This paper presents the AP19-OLR challenge focusing on three practical language identification tasks using real-world data, providing baselines and encouraging further research in oriental language recognition.

Contribution

It introduces new challenging tasks, expands language coverage, and offers baseline systems and results for the AP19-OLR challenge.

Findings

Baseline results show room for improvement in all three tasks.

More languages and real-life data increase the challenge's practical relevance.

Baseline recipes facilitate system deployment for participants.

Abstract

This paper introduces the fourth oriental language recognition (OLR) challenge AP19-OLR, including the data profile, the tasks and the evaluation principles. The OLR challenge has been held successfully for three consecutive years, along with APSIPA Annual Summit and Conference (APSIPA ASC). The challenge this year still focuses on practical and challenging tasks, precisely (1) short-utterance LID, (2) cross-channel LID and (3) zero-resource LID. The event this year includes more languages and more real-life data provided by SpeechOcean and the NSFC M2ASR project. All the data is free for participants. Recipes for x-vector system and back-end evaluation are also conducted as baselines for the three tasks. The participants can refer to these online-published recipes to deploy LID systems for convenience. We report the baseline results on the three tasks and demonstrate that the three tasks are worth some efforts to achieve better performance.