Researchers Propose New Approach to Many-to-Many Spoken Language Translation
KAIST and Google DeepMind researchers propose training a single model using Unit-to-Unit Translation to achieve seamless cross-language communication.
SlatorCon Zurich is now SOLD OUT — See you on October 4th!
KAIST and Google DeepMind researchers propose training a single model using Unit-to-Unit Translation to achieve seamless cross-language communication.
The GPT-4 powered digital visual assistant from Be My Eyes could transform accessibility for the blind and low-vision community. TTS language support is key to extending its reach.
Video conference platforms will have one year to improve live captioning, speech-to-text, and other accessibility features, according to FCC’s Report and Order.
Second funding round brings total raised to USD 21m. ElevenLabs plans to invest in voice AI research hub and vertical-specific products; speech synthesis tool supports eight languages.
Meta AI introduces Voicebox, a multilingual, multitasking generative AI model for speech, trained on 50,000 hours of audio and 20 times faster than previous models.
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.
NLP technologies drive the evolution of localization, turning jargon into common terms used to manage today’s ops and tomorrow’s strategic plans. Here are five NLP terms.
Like its competitors, Disney has partnered with voice tech startups for a Disney+ miniseries and dabbled in text-to-speech promotions; now, the company seeks experts to work in-house.
Inside look into how Pole To Win (PTW) deploys text-to-speech technology globally in delivering localization for video game, software, and technology companies.
ByteDance publishes research examining whether synthesized human speech could come close to the “impressive ability” of professional voice actors in dubbing.
Synthesia CEO Victor Riparbelli joins SlatorPod to discuss the company’s approach to personalizing video content, working with localization providers, and research at the bleeding edge of technology.
Flitto provides multilingual corpus, speech, and image data to train AI engines in 25 different languages, covering a number of domains including conversational, colloquial, and medical.
Japanese researcher-developers created an open-source all-in-one speech-to-speech translation toolkit to help machine translation researchers, and it’s publicly available on GitHub.
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