arXiv (Cornell University) · 2022 · 15 citations · 0 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingLanguage ModelingMachine TranslationMultilingual Natural Language ProcessingMultilingual ProcessingMultimodal CorporaSpeech RecognitionAutomatic RecognitionFew-shot LearningLow-resource Machine TranslationLow-resource Speech RecognitionMultilingual Speech RecognitionSpeech RetrievalSpeech UnderstandingText Retrieval
We introduce FLEURS, the Few-shot Learning Evaluation of Universal Representations of Speech benchmark. FLEURS is an n-way parallel speech dataset in 102 languages built on top of the machine translation FLoRes-101 benchmark, with approximately 12 hours of speech supervision per language. FLEURS can be used for a variety of speech tasks, including Automatic Speech Recognition (ASR), Speech Language Identification (Speech LangID), Translation and Retrieval. In this paper, we provide baselines for the tasks based on multilingual pre-trained models like mSLAM. The goal of FLEURS is to enable speech technology in more languages and catalyze research in low-resource speech understanding.