/Patent Tracker
NvidiaPatent applicationAI & softwareInterest 6/10

Nvidia patents speech-to-text system that picks the right encoder for each audio clip

Nvidia describes a system that converts spoken audio into written text by choosing one specific encoder from a group based on a label attached to the sound. The selected encoder works with a shared decoder to produce the final text output.

Why it mattersThis approach aims to make speech recognition more efficient by tailoring the processing method to the specific type of audio input.

In the filing’s own words

Approaches presented herein may be used to generate a text output of an input speech signal using an encoder from a plurality of encoders and a joint decoder associated with the plurality of encoders. The encoder may be selected based at least on a label associated with the input speech signal identifying the encoder from the plurality of encoders.

What exactly they claim (claim 1)

1. A system, comprising: one or more processors to generate a text output of an input speech signal using an encoder selected from a plurality of encoders and a joint decoder associated with the plurality of encoders, the encoder selected based at least on a label associated with the input speech signal identifying the encoder.

Facts

Company
Nvidia (Nvidia Corporation)
Official title
NATURAL LANGUAGE PROCESSING APPLICATIONS USING MULTIPLE ENCODER AND JOINT DECODER ARCHITECTURES
Publication number
US20260290351A1
Application number
19087116
Filed
Mar 21, 2025
Published
Sep 24, 2026
Inventors
4
Claims
20

Classified under

G10L 17/18 Physics & computingG10L 17/10 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Nvidia 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.