Cerence has been granted a patent for a method that involves selecting a speech recognition result on a computing device by determining whether to use the device’s result or wait for a cloud computing service’s result based on features derived from the initial speech recognition. GlobalData’s report on Cerence gives a 360-degree view of the company including its patenting strategy. Buy the report here.

Smarter leaders trust GlobalData


Premium Insights Cerence Inc - Company Profile

Buy the Report

Premium Insights

The gold standard of business intelligence.

Find out more

According to GlobalData’s company profile on Cerence, Smart voice assistant was a key innovation area identified from patents. Cerence's grant share as of February 2024 was 75%. Grant share is based on the ratio of number of grants to total number of patents.

Speech recognition result selection method on computing device

Source: United States Patent and Trademark Office (USPTO). Credit: Cerence Inc

A recently granted patent (Publication Number: US11929073B2) outlines a method for selecting a speech recognition result on a computing device. The method involves acquiring speech data for an utterance, soliciting speech recognition results from both the computing device and a cloud computing service, receiving the results, and determining whether to select the first result or wait for the second based on various features. These features include a confidence value computed for the first result, which is compared to a predetermined threshold to make the selection. The method also involves processing the features using a classifier, potentially implemented as a neural network, to characterize the quality of the recognition result.

Furthermore, the patent describes a system and software for implementing this method, including components for acquiring speech data, soliciting recognition results, receiving features, and making the selection based on the determined criteria. The software stored on a computer-readable medium provides instructions for processors to perform the steps involved in selecting a speech recognition result. The method not only focuses on selecting the best recognition result but also on subsequent processing and potential actions based on the selected result. Overall, the patent details a comprehensive approach to optimizing speech recognition on computing devices by leveraging both local and cloud-based services and utilizing various features to make informed decisions.

To know more about GlobalData’s detailed insights on Cerence, buy the report here.

Premium Insights


The gold standard of business intelligence.

Blending expert knowledge with cutting-edge technology, GlobalData’s unrivalled proprietary data will enable you to decode what’s happening in your market. You can make better informed decisions and gain a future-proof advantage over your competitors.


GlobalData, the leading provider of industry intelligence, provided the underlying data, research, and analysis used to produce this article.

GlobalData Patent Analytics tracks bibliographic data, legal events data, point in time patent ownerships, and backward and forward citations from global patenting offices. Textual analysis and official patent classifications are used to group patents into key thematic areas and link them to specific companies across the world’s largest industries.