A new broad-based language model, trained specifically for certain tasks, balances training data to promote equal representation across language and improves accuracy up to 50%.
Meta says its new system, which offers text-to-speech and speech-to-text for more than 1,100 languages, has half the word error rate of Whisper. Critics say, Apples and oranges.
Breakthroughs in multilingual speech models are rapidly expanding language coverage for ASR. But what about endangered languages with little to no training data?
As the language industry turns to speech-to-speech translation, Facebook AI partners with “AI community” Hugging Face to release speech-to-text translation models for four languages.
Zoom call add-ons planned for beta release in September 2021. Transcription available in 30 languages, and translation, in 12, by year-end 2022.
US and Chinese tech giants continue to churn out research on speech-to-text translation, machine translation for rare languages, and more. Time to check in.
MT and speech recognition company AppTek expands natural language understanding (NLU) capabilities with acquisition of speech technology provider Ignite-Tek.
Four college students harnessed recent Google Cloud releases to build a translation app that works offline and makes forms accessible to users with disabilities.
UN asks vendors to pitch solutions for remote interpreting, neural machine translation, speech-to-text, etc. to secure one of 25 spots at January 2020 conferencing tech fair in Geneva.
Slator Weekly: Join over 15,800 subscribers and get the latest language industry intelligence every Friday
Tool Box: Join 10,000 subscribers for your monthly linguist technology update.
Your information will not be shared with third parties. No Spam.
This will close in 0 seconds
