NIRANTAR: Continual Learning with New Languages and Domains on Real-world Speech Data
This addresses the need for robust continual learning strategies in real-world ASR applications, though it is incremental as it focuses on benchmarking rather than proposing new methods.
The authors tackled the problem of evaluating continual learning in multilingual and multi-domain automatic speech recognition by introducing Nirantar, a framework with 3250 hours of real-world speech data across 22 languages and 208 districts, and found that no existing method performed consistently well across scenarios.
We introduce Nirantar, a comprehensive framework for evaluating continual learning (CL) in multilingual and multi-domain ASR. Designed to reflect real-world CL challenges, Nirantar leverages data collected incrementally across 22 languages and 208 districts in India through natural episodes. This enables evaluation across Language-Incremental (LIL), Domain-Incremental (DIL), and the novel Language-Incremental Domain-Incremental Learning (LIDIL) scenarios. Unlike prior work that relies on simulated episodes, Nirantar presents dynamic, non-uniform language and domain shifts, making it an ideal testbed for CL research. With 3250 hours of human-transcribed speech, including 1720 hours newly introduced in this work, our framework enables systematic benchmarking of CL methods. We evaluate existing approaches and demonstrate that no single method performs consistently well, underscoring the need for more robust CL strategies.