XTREME-S: Evaluating Cross-lingual Speech Representations
Alexis Conneau, Ankur Bapna, Yu Zhang, Min Ma, Patrick von Platen, Anton Lozhkov, Colin Cherry, Jia Ye, Clara Rivera, Mihir Kale, Daan van Esch, Vera Axelrod, Simran Khanuja, Jonathan R. Clark, Orhan Fırat, Michael Auli, Sebastian Ruder, Jason Riesa, Melvin Johnson · Interspeech 2022 · 2022
We introduce XTREME-S, a new benchmark to evaluate universal cross-lingual speech representations in many languages.XTREME-S covers four task families: speech recognition, classification, speech-to-text translation and retrieval.Covering 102 languages from 10+ language families, 3 different domains and 4 task families, XTREME-S aims to simplify multilingual speech representation evaluation, as well as catalyze research in "universal" speech representation learning.This paper describes the new benchmark and establishes the first speech-only and speechtext baselines using XLS-R and mSLAM on all downstream tasks.We motivate the design choices and detail how to use the benchmark.Datasets and fine-tuning scripts are made easily accessible through the HuggingFace platform. 1