A Survey of Multilingual Models for Automatic Speech Recognition
This is an incremental survey that synthesizes existing research to guide development of ASR systems for low-resource languages, benefiting researchers and practitioners in speech technology.
The paper surveys state-of-the-art multilingual automatic speech recognition models that use cross-lingual transfer to address the lack of large speech datasets for low-resource languages, highlighting best practices and open questions without reporting specific performance numbers.
Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due to the lack of large speech datasets to train these models. Cross-lingual transfer is an attractive solution to this problem, because low-resource languages can potentially benefit from higher-resource languages either through transfer learning, or being jointly trained in the same multilingual model. The problem of cross-lingual transfer has been well studied in ASR, however, recent advances in Self Supervised Learning are opening up avenues for unlabeled speech data to be used in multilingual ASR models, which can pave the way for improved performance on low-resource languages. In this paper, we survey the state of the art in multilingual ASR models that are built with cross-lingual transfer in mind. We present best practices for building multilingual models from research across diverse languages and techniques, discuss open questions and provide recommendations for future work.