US 8306815

A concise summary of US Patent 8,306,815 is as follows:

Title: Speech dialog control based on signal pre-processing

Assignee: Harman Becker Automotive Systems GmbH and Cerence Operating Co are listed as current assignees. The original assignee was Nuance Communications Inc.

Inventors:

• Lars König
• Gerhard Uwe Schmidt
• Andreas Löw

Filing Date: December 6, 2007

Issue Date: November 6, 2012

Abstract:
A speech dialog system interfaces a user to a computer. The system includes a signal pre-processor that processes a speech input to generate an enhanced signal and an analysis signal. A speech recognition unit may generate a recognition result based on the enhanced signal. A control unit may manage an output unit or an external device based on the information within the analysis signal.

Plain-Language Overview of Independent Claims:

Independent Claim 1: This claim describes a speech dialog system that includes a processor and several interconnected units. A "signal pre-processor unit" takes a person's speech, cleans it up to create an "enhanced speech signal," and also generates an "analysis signal" that contains information about the characteristics of the speech that are not related to the words themselves (like background noise or the speaker's pitch). A "speech recognition unit" then figures out the words spoken from the cleaned-up signal. A "speech output unit" provides a spoken response. Finally, a "speech dialog control unit" uses the analysis of the speech characteristics to control the spoken response, and it also uses the recognized words to control the initial signal pre-processor.

Independent Claim 20: This claim outlines a similar speech dialog system, but with a more direct feedback loop. It includes a "signal pre-processor unit" that cleans up a speech signal, a "speech recognition unit" that determines the words spoken, and a "speech dialog control unit." The key aspect of this claim is that the control unit takes the recognized words and uses that information to control the initial signal pre-processor.

Independent Claim 22: This claim describes the method or the steps the system takes to operate. It involves a processor performing several actions: processing a speech input to create a cleaned-up version, analyzing the speech to understand its non-semantic characteristics, figuring out the words spoken, providing a spoken output in response to those words, controlling that spoken output based on the non-semantic characteristics, and adjusting how the initial speech is processed based on the words that were recognized.

Independent Claim 23: This claim covers a computer program product, which means software stored on a non-transitory computer-readable medium (like a hard drive or memory chip). The software contains instructions for a computer to perform the same method described in Claim 22: processing speech, analyzing its characteristics, recognizing the words, providing a spoken response, and then controlling that response and the initial processing based on the characteristics and the recognized words.

Regarding a search of the CAFC (Court of Appeals for the Federal Circuit) 2026 dockets for this patent, no results were found. It is important to note that searching for future court dockets is speculative, and the absence of results does not preclude the possibility of future litigation.