Tapping into whale talk: Open-source bio-logger captures underwater cetacean conversations

Say you want to listen in on a group of super-intelligent aliens whose language you don't understand, and whose spaceship ...

Google Translate finally understands what you meant, not just what you typed

Google is upgrading Translate with Gemini-powered context-aware translations, live speech translation through headphones, and ...

Google is turning any headphones into real-time translation earbuds

Starting today, Android device owners can begin testing live speech translation in the Google Translate app, which now relies on Gemini. The AI makes text translations ...
GitHub

Kokoro Web - Free AI Text to Speech

Kokoro Web is powered by hexgrad/Kokoro-82M, an open-weight 82 million parameter Text-to-Speech model available on Hugging Face. Despite its lightweight architecture, it delivers comparable quality to ...

Five thoughts from CEO Matt Garman’s keynote at AWS re:Invent

Amazon Web Services Inc. Chief Executive Matt Garman’s keynote at AWS re:Invent was filled with product updates with vision ...
IEEE

From Characters to Subwords: Modeling Unit Conversion for Low-resource Speech Recognition

Abstract: Multilingual automatic speech recognition (ASR) models greatly facilitate recognizing low-resource languages by sharing representations across similar languages. However, the commonly ...