Meta Expands AI Speech Recognition to 1,600+ Languages

Omnilingual Automatic Speech Recognition can transcribe speech in over 1,600 languages — including 500 low-resource languages ...
PCMag on MSN

Meta AI Transcribes 500 Niche Languages for the First Time, Admits It's Not Perfect

The system also allows people to upload their own voice snippets, which Meta says is a more scalable way to bridge the digital divide for languages that are underrepresented online.
IEEE

AVE Speech: A Comprehensive Multimodal Dataset for Speech Recognition Integrating Audio, Visual, and Electromyographic Signals

Abstract: The global aging population faces considerable challenges, particularly in communication, due to the prevalence of hearing and speech impairments. To address these, we introduce the AVE ...
IEEE

Speech Few-Shot Learning for Language Learners’ Speech Recognition

Abstract: This paper reports how speech recognition accuracy can be improved using the speech few-shot in-context learning capabilities of a multimodal foundation model when applied to the speech of ...