Samsung Patents a Voice Search That Understands Full Sentences, Not Just Keywords
Most voice search on devices today is keyword-matching in disguise. Samsung is filing patents for something that actually understands what you meant…
126 filings · category
Voice & speech AI patents
Machines that listen and talk back: transcription, translation, synthetic voices, and the systems that clean up how we sound.
Recent filings
126 total
Real-Time Voice Translation Patent Preserves Each Speaker's Tone
Samsung is working on a translator that doesn't just convert words from one language to another. It also tries to carry over…
Samsung Patents a System That Reviews Your Voice Command History to Show What Works
Most voice assistants fail silently, leaving you to guess whether you phrased something wrong or the assistant just gave up. Samsung is…
Samsung Patents a Voice Assistant That Remembers What You Asked Before
Most voice assistants treat every question like the first one you've ever asked. Samsung is patenting a way to change that, by…
New Patent Turns Unclear or Stuttered Speech Into Clean Audio for Each Speaker
Google is patenting a system that takes the speech of someone with a stutter, dysarthria, or other atypical speech pattern and converts…
Samsung Patents an Audio Editor That Lets You Adjust Tracks Before the AI Finishes Splitting Them
Samsung is patenting an audio editor that shows you individual volume controls for voice, music, and background noise the moment it recognizes…
Nvidia Patents an AI System That Recreates Voices From Audio Recordings
Nvidia is patenting a way to teach AI systems to think about a person's voice in three separate layers at once: who…
Samsung Patents AI That Scrubs Unwanted Sounds Twice for Cleaner Audio
Most AI noise-removal tools leave behind faint ghost traces of the sounds they were supposed to erase. Samsung's new patent attacks those…
Microsoft Patent Routes AI Customers to Better-Matched Server Instances Based on Usage
When you ask an AI to transcribe audio one minute and analyze an image the next, the underlying hardware you're running on…
Microsoft Patent Reuses Voice AI Training Data Across Different Microphone Configurations
Training a voice AI from scratch for every new microphone setup is expensive and slow. Microsoft's new patent describes a way to…
Google Patents On-Device Audio That Strips Out Every Voice Except Yours
Imagine being on a noisy call and having your phone automatically strip away every voice except the person you asked it to…
Nvidia Patents a Way to Blend Real Voices Into New Synthetic Ones
Nvidia has filed a patent for a text-to-speech system that doesn't just copy a single speaker's voice — it blends two or…
Get the weekly Patentlyze email
We read every patent application Big Tech publishes and send you the ones worth knowing. Plain English, free, every week.