SIGTYP 2021 Shared Task: Robust Spoken Language Identification
This work addresses the problem of making language identification accessible for low-resource and endangered languages, though it is incremental in highlighting existing limitations.
The paper tackled the challenge of robust spoken language identification under domain and speaker mismatch, finding that current methods achieve over 95% accuracy in-domain but struggle significantly in cross-domain scenarios, with domain adaptation offering limited improvement.
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.