/Patent Tracker
NvidiaPatent applicationAI & softwareInterest 7/10

Nvidia patents model that turns speech into text in any language

Nvidia describes a single machine learning model that handles both speech recognition and language translation at the same time. It takes audio input and a target language, mixes the sound data with language data, and outputs text in the chosen language.

Why it mattersThis approach could make voice assistants and translation tools more efficient by combining two separate steps into one process.

In the filing’s own words

In various examples, multilingual speech processing models for speech processing systems and applications is described here. Systems and methods described herein may use an end-to-end model that is capable of performing both ASR processing and translation processing to generate text in various languages. For instance, a user may provide at least audio data representing speech along with an indication of a target language for translating the speech. The model may then generate one or more audio representations associated with the speech along with one or more language representations associated with the target language. Additionally, the model may combine the audio representation(s) with the language representation(s)-such as by performing concatenation, masking, fusion, adding, and/or the like-to generate one or more combined representations. The model may then process the combined representation(s) to generate text corresponding to the speech and in the target language.

What exactly they claim (claim 1)

1. A method comprising: generating, using one or more first encoders of one or more machine learning models and based at least on audio data representative of speech, one or more audio vectors associated with an embedding space; generating, using the one or more machine learning models, one or more language vectors corresponding to a target language; generating one or more combined vectors based at least on the one or more audio vectors and the one or more language vectors; generating, using one or more decoders of the one or more machine learning models and based at least on the one or more combined vectors, output data representative of text corresponding to the speech and in the target language; and causing an output associated with the text.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
MULTILINGUAL SPEECH RECOGNITION MODELS FOR SPEECH PROCESSING SYSTEMS AND APPLICATIONS
Publication number
US20260260655A1
Application number
19066468
Filed
Feb 28, 2025
Published
Sep 3, 2026
Inventors
4
Claims
20

Classified under

G10L 15/26 Physics & computingG10L 15/005 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.