Nvidia Patents a Speech Recognizer That Outputs Multiple Transcript Formats at Once
Most speech recognition systems give you one transcript. Nvidia's new patent describes a single model that listens once and hands back several…
Machines that listen and talk back: transcription, translation, synthetic voices, and the systems that clean up how we sound.
Most speech recognition systems give you one transcript. Nvidia's new patent describes a single model that listens once and hands back several…
Google is patenting a system that acts like a personalized radio DJ, where an AI picks music for you and then lowers…
Most AI writing tools sound like AI. Microsoft is filing a patent for a system that's supposed to sound like you, by…
Training an AI translator is hard when real recorded speech is scarce. Samsung's answer: fill the gaps with synthetic voices and teach…
Google has filed a patent for a speech recognition system that doesn't just listen to what you say, it also checks a…
Most voice assistants treat every sentence you speak as if it's the first thing you've ever said. Google is patenting a system…
When you tell a voice assistant to 'order coffee,' it has to guess which app you want. Google is patenting a system…
When Google trains its speech recognition AI on real recordings, the model might memorize fragments of people's voices without anyone intending it…
Most voice assistants just try to do what you ask and fail silently. Samsung's new patent describes one that first checks whether…
What if you could tell a robot to 'move smoothly to the left and slow down near the edge' and it actually…
Nvidia is building an AI that listens to how you speak, not just what you say, and uses the emotion it detects…
Say one phrase to Siri and watch it complete a chain of tasks across different apps, telling you how each one went.…
One Big Tech patent every Sunday. Free.