SIGTYP 2021 Shared Task: Robust Spoken Language Identification
Abstract
While language identification is a fundamental speech and language processing task, for many languages and language families it remains a challenging task. For many low-resource and endangered languages this is in part due to resource availability: where larger datasets exist, they may be single-speaker or have different domains than desired application scenarios, demanding a need for domain and speaker-invariant language identification systems. This year's shared task on robust spoken language identification sought to investigate just this scenario: systems were to be trained on largely single-speaker speech from one domain, but evaluated on data in other domains recorded from speakers under different recording circumstances, mimicking realistic low-resource scenarios. We see that domain and speaker mismatch proves very challenging for current methods which can perform above 95% accuracy in-domain, which domain adaptation can address to some degree, but that these conditions merit further investigation to make spoken language identification accessible in many scenarios.
Cite
@article{arxiv.2106.03895,
title = {SIGTYP 2021 Shared Task: Robust Spoken Language Identification},
author = {Elizabeth Salesky and Badr M. Abdullah and Sabrina J. Mielke and Elena Klyachko and Oleg Serikov and Edoardo Ponti and Ritesh Kumar and Ryan Cotterell and Ekaterina Vylomova},
journal= {arXiv preprint arXiv:2106.03895},
year = {2021}
}
Comments
The first three authors contributed equally