/Patent Tracker
GoogleGranted patentAI & softwareInterest 6/10

Google patents method to separate voices in video calls using AI

Google has been granted a patent for a system that takes mixed audio from a video conference and breaks it down into small digital units called tokens. A machine learning model then groups these tokens to identify individual speakers, allowing the system to create separate transcripts for each person talking.

Why it mattersThis technology could improve how video conferencing tools record and organize conversations by automatically distinguishing between different speakers in a noisy or overlapping audio stream.

In the filing’s own words

A system and method are disclosed. Audio input comprising the mixed audio signals is received by one or more client devices. The audio input is converted into a plurality of discrete tokens. A plurality of sound sources, each corresponding to a subset of discrete tokens of a plurality of subsets of discrete tokens, is determined using a trained machine learning model.

What exactly they claim (claim 1)

1. A method comprising: receiving audio input comprising mixed audio signals provided by one or more client devices of one or more users of a video conference platform that participate in a video conference; converting the audio input into a plurality of discrete tokens comprising one or more of a plurality of acoustic tokens, which capture at least sound events or acoustic characteristics within the mixed audio signals, or a plurality of semantic tokens, which are derived from text data extracted from the mixed audio signals and capture at least associated meanings and contextual representations of words or subword units, wherein converting the audio input into the plurality of discrete tokens comprises: providing, to a first machine learning model, input comprising the audio input; and obtaining, from the first machine learning model, one or more outputs identifying the plurality of discrete tokens; and determining, using a second machine learning model, a plurality of sound sources each corresponding to a subset of discrete tokens of a plurality of subsets of discrete tokens, wherein a transcript of at least one of the plurality of sounds sources is generated for the video conference.

Facts

Company
Google (Google LLC)
Official title
Using machine learning and discrete tokens to estimate different sound sources from audio mixtures
Patent number
US12744045B2
Application number
18233323
Filed
Aug 13, 2023
Granted
Sep 22, 2026
Inventors
7
Claims
19

Classified under

G10L 17/20 Physics & computingG10L 17/02 Physics & computingG10L 17/04 Physics & computingG10L 17/06 Physics & computingG10L 17/18 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Google in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.