AI brief
Apple Machine Learning Research reports that strengthening a multilingual speech model's ability to discriminate between languages improves its linguistic learning, addressing the gap between multilingual and monolingual models under matched pretraining data budgets.
Why it matters: It suggests a way for multilingual speech models to close the performance gap with monolingual models without increasing total pretraining data.
Written by AI from Apple Machine Learning Research's published text.
Source
“Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models.”
A paper, laboratory publication or research report.
Read original story ↗