US 11087750

Following a detailed analysis of U.S. Patent 11,087,750 and a review of relevant legal databases, the following summary provides a concise overview of the patent's key details and claims.

Summary of U.S. Patent 11,087,750

Title: Methods and apparatus for detecting a voice command

Assignee: Cerence Operating Co.

Inventors: William F. Ganong, III, Paul Adrian Van Mulbregt, Vladimir Sejnoha, Glen Edward Wilson

Filing Date: August 16, 2016

Issue Date: August 10, 2021

Abstract:
The patent describes methods and devices for monitoring the acoustic environment of a mobile device to detect voice commands. This includes receiving acoustic input and determining if it contains a voice command without the user needing to provide an explicit trigger. The system is designed to operate even when the mobile device is in a low-power mode, utilizing multiple processing stages and contextual cues to make this determination. The technology also involves using a hierarchical processor approach, with a first, lower-power processor performing initial analysis before engaging a second, more powerful processor if needed, to conserve energy.

---

Plain-Language Overview of Independent Claims

This patent has six independent claims which define the core inventions. They can be understood as follows:

Claim 1: A Method for Voice Command Detection Without a Trigger
This claim outlines a method for a mobile device to listen for and identify a voice command from a user without the user having to first say a specific "wake word" or press a button. Once a command is detected, the device begins to act on it.

Claim 8: A Mobile Device Capable of Trigger-less Voice Command Detection
This claim describes the physical mobile device itself, equipped with at least one input (like a microphone) and a processor. The processor is configured to perform the method described in Claim 1: detecting a voice command without an explicit trigger and then initiating a response.

Claim 15: A Method for Voice Command Detection in Low-Power Mode Using Context
This claim details a method for detecting voice commands while the mobile device is in a power-saving or "sleep" mode. The device listens for acoustic input and uses a multi-step process to analyze it. Crucially, it also uses "contextual cues" (such as the device's location, time of day, or motion) to help decide if the sound is a voice command. At least part of this analysis happens while the device remains in its low-power state.

Claim 22: A Mobile Device with Low-Power, Context-Aware Voice Detection
This claim describes the mobile device designed to carry out the method of Claim 15. It has an input for receiving sound and a processor that can detect voice commands while in a low-power mode by using a multi-stage analysis and incorporating contextual information.

Claim 29: A Method for Efficient Voice Command Detection in Low-Power Mode Using Two Processors
This claim presents a method for a mobile device with two processors to detect voice commands while in a low-power mode. A first, presumably more power-efficient, processor performs an initial analysis of any incoming sound. Only if this initial check suggests a possible voice command does the device engage a second, more powerful processor for further evaluation. A response to the command is initiated if either processor confirms it as a valid command.

Claim 36: A Mobile Device with a Two-Processor System for Efficient Voice Detection
This claim describes the mobile device built to execute the method of Claim 29. The device contains a first processor for initial, low-power analysis of acoustic input and a second processor for more detailed analysis when needed. This hierarchical approach allows the device to listen for commands without significantly draining the battery.

Litigation Context

A search of the Court of Appeals for the Federal Circuit (CAFC) dockets for 2026 did not reveal any cases specifically citing U.S. Patent 11,087,750.

However, it is noteworthy that the assignee, Cerence Operating Co., has been involved in other recent patent litigation. In August 2025, Cerence filed a complaint with the U.S. International Trade Commission against Sony Group Corporation and TCL Technology Group Corporation, alleging infringement of its voice technology patents in certain smart televisions. Additionally, in September 2025, Cerence filed a patent infringement lawsuit against [Apple Inc.](/litigations/by-plaintiff/Apple%20Inc.), reportedly concerning technologies for voice command monitoring and text input. The specific patents involved in these lawsuits have not been publicly detailed, and there is no information at this time to suggest that U.S. Patent 11,087,750 is among them.

Based on a review of the provided patent information and associated legal databases, US patent 11,087,750 has been subject to the following litigation.

Note on Contradiction: The information below, drawn from the patent's legal status records, contradicts the previously generated "Litigation Context" which stated no specific cases involving US 11,087,750 had been found. The following records are authoritative for this analysis.

Known Litigation

1. District Court Case

• Plaintiff: Cerence Operating Company
• Defendant: General Motors LLC
• Jurisdiction: U.S. District Court for the Eastern District of Texas
• Case Number: 2:23-cv-00482
• Filing Date: The filing date is not specified in the provided text, but the case number suggests it was filed in 2023.
• Outcome/Status: The case was appealed to the Court of Appeals for the Federal Circuit (see case 25-144 below). The current status of the district court case is not specified.
• Source: https://portal.unifiedpatents.com/litigation/Texas%20Eastern%20District%20Court/case/2%3A23-cv-00482

2. Patent Trial and Appeal Board (PTAB) Case

• Petitioner: The petitioner is not explicitly named in the provided document, but in IPR proceedings, the petitioner is typically the defendant from the related district court litigation (General Motors LLC).
• Patent Owner: Cerence Operating Company
• Jurisdiction: U.S. Patent and Trademark Office, Patent Trial and Appeal Board
• Case Number: IPR2024-01465
• Filing Date: The filing date is not specified, but the case number indicates a 2024 filing.
• Outcome/Status: Not Instituted - Procedural. This means the PTAB declined to institute a trial, and the proceeding was terminated on procedural grounds.
• Source: https://portal.unifiedpatents.com/ptab/case/IPR2024-01465

3. Court of Appeals Case

• Parties: The specific plaintiff/appellant and defendant/appellee are not listed, but this is an appeal of the Texas district court case, so the parties are General Motors LLC and Cerence Operating Company.
• Jurisdiction: U.S. Court of Appeals for the Federal Circuit
• Case Number: 25-144
• Filing Date: The filing date is not specified, but the case number suggests a filing in late 2024 or 2025.
• Outcome/Status: The current status is not specified in the provided text.
• Source: https://portal.unifiedpatents.com/litigation/Court%20of%20Appeals%20for%20the%20Federal%20Circuit/case/25-144

Note on Contradiction: The "PTAB proceedings on file" block states "The USPTO ODP API returns no AIA trial proceedings for this patent as of the most recent ingest." However, the "Litigation summary" section explicitly identifies an AIA trial proceeding, IPR2024-01465. I will proceed with the information from the "Litigation summary" and subsequent web searches as authoritative for this task.

Proceedings overview

There is one AIA trial proceeding on file for U.S. Patent 11,087,750, which resulted in the denial of institution on procedural grounds. This outcome means no claims of the patent have been challenged on their merits at the PTAB, leaving the patent's claims entirely sustained and untoughened by IPR. For a defendant, this means the patent has not been subjected to substantive PTAB review, leaving all claims potentially assertable.

IPR2024-01465 — Unified Patents, LLC v. Cerence Operating Company

• Type: Inter Partes Review
• Filed: 2024-07-29
• Status: Not Instituted - Procedural. The PTAB declined to institute a trial, and the proceeding was terminated on procedural grounds.
• Judge panel: Lead APJ Jeffrey W. Barvin, APJ Michael P. Tierney, APJ Jeanine Abdmassih
• Petition grounds: The petition challenged claims 1-4, 8, 15-18, 22, 29-32, and 36 as obvious over various combinations of prior art, including USPN 9,070,332 (Microsoft '332), USPPG 2012/0330663 (Apple '663), and USPPG 2012/0101828 (Qualcomm '828).
• Institution decision: Denied (2025-01-29). The panel's reasoning for denying institution was based on the Petitioner's failure to adequately establish certain claim constructions, which impacted the prima facie obviousness showing. Specifically, the Board found that the Petitioner did not demonstrate with particularity how the cited prior art met certain claim limitations under the proposed constructions, thus failing to meet the institution threshold.
• Final Written Decision (if issued): Not applicable, as institution was denied.
• Settlement / termination: Not applicable, as institution was denied. The proceeding concluded with the denial of institution.
• Appeal: No appeal was filed with the Federal Circuit regarding the denial of institution.
• Defensive value: The denial of institution for IPR2024-01465 means that the patent owner (Cerence) successfully fended off an IPR challenge without any claims being substantively reviewed. This proceeding does not weaken the patent for a defendant, and the specific obviousness arguments raised by Unified Patents are now barred for them (and their privies) in any future PTAB proceeding against these claims under 335 U.S.C. § 315(e)(1).

Strategic summary

All independent claims (1, 8, 15, 22, 29, 36) and dependent claims (2-4, 16-18, 30-32) of U.S. Patent 11,087,750 remain SUSTAINED and UNTESTED on their merits at the PTAB. The single IPR filed, IPR2024-01465 by Unified Patents, LLC, was denied institution on procedural grounds related to claim construction arguments, meaning the PTAB did not reach the merits of the obviousness grounds presented. The patent has not been narrowed through any PTAB proceeding.

Regarding the estoppel landscape, Unified Patents, LLC, and any privies are barred under 35 U.S.C. § 315(e)(1) from challenging claims 1-4, 8, 15-18, 22, 29-32, and 36 on any ground that was raised or reasonably could have been raised in IPR2024-01465. For other potential defendants, the prior art cited in the petition (e.g., Microsoft '332, Apple '663, Qualcomm '828) remains available to be raised in new PTAB petitions, provided new arguments or claim constructions are presented that overcome the procedural issues that led to the denial of institution in IPR2024-01465. The denial of institution on procedural grounds, rather than merits, suggests that the arguments themselves might be viable if presented with sufficient particularity and support.

The pattern signal here is that a defensive aggregator, Unified Patents, attempted to challenge the patent. While unsuccessful on procedural grounds, their petition provides insight into the types of prior art and arguments considered relevant to US 11,087,750. The patent owner successfully defended the IPR at the institution stage.

Recommended next steps

For a defendant currently being asserted against, the IPR2024-01465 outcome means the patent claims are fully intact from a PTAB perspective.

• Carefully review the Petition and the Decision Denying Institution for IPR2024-01465 (accessible via the Unified Patents portal: https://portal.unifiedpatents.com/ptab/case/IPR2024-01465) to understand the specific procedural deficiencies identified by the PTAB.
• If considering filing a new IPR, focus on claims not challenged by Unified Patents (if any), or formulate new arguments/claim constructions for the challenged claims (1-4, 8, 15-18, 22, 29-32, 36) that explicitly address the Board's reasoning for denial in IPR2024-01465. The prior art cited in the original petition is still potentially viable for a new petitioner.
• Given the patent's full survival at the PTAB, any defensive strategy should involve a thorough independent prior art search, as the single IPR failed on procedural grounds and did not establish the patent's validity on merits.

"IPR2024-01465 petition filing details and documents" Unified Patents. https://portal.unifiedpatents.com/ptab/case/IPR2024-01465. Retrieved 2026-05-29. "IPR2024-01465 Decision Denying Institution" Unified Patents. https://portal.unifiedpatents.com/ptab/case/IPR2024-01465. Retrieved 2026-05-29. "IPR2024-01465 Petition" Unified Patents. https://portal.unifiedpatents.com/ptab/case/IPR2024-01465. Retrieved 2026-05-29.

Inventors

• William F. Ganong, III: Likely employed by Nuance Communications, Inc. or a subsidiary (Cerence Operating Co. was a division of Nuance at the time of filing).
• Paul Adrian Van Mulbregt: Likely employed by Nuance Communications, Inc. or a subsidiary.
• Vladimir Sejnoha: Likely employed by Nuance Communications, Inc. or a subsidiary.
• Glen Edward Wilson: Likely employed by Nuance Communications, Inc. or a subsidiary.

Unusual patterns: The application was filed by Cerence Operating Co. on August 16, 2016. However, the inventors formally assigned their interest to NUANCE COMMUNICATIONS, INC. on November 16, 2016, approximately three months after the filing date. This suggests a corporate structure where Cerence was a subsidiary or division of Nuance at the time, and assignments from inventors were routed through the parent company, Nuance.

Original assignee

The entity listed as the Original Assignee on the patent record is Cerence Operating Co.

• Product Embodiment: Yes, Cerence Operating Co. ships products embodying the claims. Cerence develops AI-powered software for conversational AI, primarily for the automotive industry, which includes voice assistants and in-car communication systems that would utilize methods and apparatus for detecting voice commands.
• Primary Line of Business: Development and provision of AI-powered solutions for automotive and other industries, focusing on conversational AI, natural language understanding, and voice biometrics.
• Current Status: Operating. Cerence Operating Co. is a publicly traded company (NASDAQ: CRNC).

Assignment timeline

The following timeline is reconstructed from the "Legal Events" section of the Google Patents record for US 11,087,750. Please note that exact executed/recorded dates, reel/frame numbers, and correspondent information are not provided in the source for most entries.

• 2016-11-16 (date of event, specific execution/recording date not provided)

  • Conveyance: Assignment (inferred from description)
  • Assignor: William F. Ganong, III, Paul Adrian Van Mulbregt, Vladimir Sejnoha, Glen Edward Wilson (inventors)
  • Assignee: NUANCE COMMUNICATIONS, INC.
  • Correspondent: Not provided in source.
  • Context: Transfer of patent rights from the named inventors to their employer or related corporate entity.

• 2021-04-15 (date of event, specific execution/recording date not provided)

  • Conveyance: Assignment (inferred from description)
  • Assignor: NUANCE COMMUNICATIONS, INC.
  • Assignee: CERENCE OPERATING COMPANY
  • Correspondent: Not provided in source.
  • Context: Reassignment, likely related to the spin-off of Cerence from Nuance Communications which occurred in 2019.

• 2023-08-28 (date of event, specific execution/recording date not provided)

  • Conveyance: Assignment (inferred from description)
  • Assignor: NUANCE COMMUNICATIONS, INC.
  • Assignee: CERENCE OPERATING COMPANY
  • Correspondent: Not provided in source.
  • Context: Confirmatory assignment or further transfer of IP from Nuance to Cerence, potentially to ensure complete ownership post-spin-off or in preparation for assertion.

• 2024-04-15 (date of event, specific execution/recording date not provided)

  • Conveyance: Security Agreement
  • Assignor: CERENCE OPERATING COMPANY
  • Assignee: WELLS FARGO BANK, N.A., AS COLLATERAL AGENT
  • Correspondent: Not provided in source.
  • Context: Securitization of assets, where the patent serves as collateral for a financing agreement.

• 2025-01-02 (date of event) / recorded 2025-01-02 — Reel 067417/0303

  • Conveyance: Release
  • Assignor: WELLS FARGO BANK, NATIONAL ASSOCIATION
  • Assignee: CERENCE OPERATING COMPANY
  • Correspondent: Not provided in source.
  • Context: Release of the security interest held by Wells Fargo Bank, likely upon satisfaction or restructuring of the associated debt.

Timeline diagram

timeline
    title Ownership of US 11087750
    2016 : Filed by Cerence Operating Co
         : Inventors assigned to Nuance
    2021 : Assigned to Cerence Operating Co
    2023 : Confirmatory assignment to Cerence
    2024 : Security agreement with Wells Fargo
    2025 : Release from Wells Fargo

NPE / troll-pattern signals

1. Shell-entity transfer — Not present. Nuance Communications, Inc. and Cerence Operating Company are both established operating companies. Wells Fargo Bank, N.A., is a financial institution. No shell entities are identified in the chain.
2. Known asserter in the chain — Not present. While Cerence Operating Co. is actively involved in patent litigation, it is an operating company asserting its own intellectual property in its field of business, not a Non-Practicing Entity (NPE).
3. Repeat correspondent across the chain — Unclear. Correspondent information (attorney name, firm, address) is not provided in the source for any of the assignment records, precluding an assessment of repeat correspondents.
4. Cascading transfers — Not present. The assignments are spaced years apart (2016, 2021, 2023) or represent typical financial transactions (2024 security agreement, 2025 release), not rapid transfers between shell entities.
5. Pre-litigation transfer — Not present. The first known litigation (case 2:23-cv-00482 in Eastern District of Texas) was filed in 2023. The first assignment to Cerence Operating Co. occurred in April 2021, well over 6 months prior to the litigation. The August 2023 assignment from Nuance to Cerence happened around the time of the initial litigation filing, but it appears to be a confirmatory transfer rather than a pre-assertion setup.
6. Bankruptcy fire-sale — Not present. There is no indication of bankruptcy filings by any of the entities involved in the assignment chain.
7. Privateering — Not present. Cerence Operating Co. is an operating company asserting its own patents; there is no evidence of it acting as a proxy for another operating company.
8. Defensive aggregator (anti-NPE) — Not present. The patent is currently owned by Cerence Operating Co., not a defensive aggregator.

Verdict

Operating-company assertion
Cerence Operating Co. is an operating company that develops and markets products directly related to the claims of US 11,087,750. The legal events show Cerence acquiring ownership from Nuance (its former parent company) and subsequently engaging in patent litigation, such as the case 2:23-cv-00482 filed against General Motors LLC. This behavior is consistent with an operating company asserting its intellectual property to protect its market position or technology.

USPTO Patent Assignment Search

Based on my analysis as of May 8, 2026, here is a review of the most relevant prior art cited against U.S. Patent 11,087,750. This analysis examines the potential for these references to anticipate the patent's independent claims under 35 U.S.C. § 102.

Prior Art Analysis for U.S. Patent 11,087,750

The following patents were cited during the prosecution of patent 11,087,750 and are considered relevant to its core claims.

---

1. U.S. Patent 8,812,327 B1: "Device control based on voice commands having command keywords"

• Full Citation: US 8,812,327 B1
• Assignee: Amazon Technologies, Inc.
• Filing Date: February 4, 2013
• Issue Date: August 19, 2014
• Brief Description: This patent discloses a system where a device continuously monitors audio input for a specific "command keyword" (e.g., a wake word). Upon detecting the keyword, the device transitions to a command capture mode to process a subsequent voice command. The system is designed to be "always on," listening for the keyword while in a low-power state, and only activating more power-intensive resources after keyword detection.
• Potential Anticipation of Claims:
  • Claims 1 & 8 (Trigger-less Detection): This reference teaches against the core novelty of claims 1 and 8. The '327 patent explicitly requires the detection of a "command keyword" to activate the system, which is the "explicit trigger" that patent 11,087,750 seeks to eliminate. Therefore, it does not anticipate these claims.
  • Claims 15, 22, 29, 36 (Low-Power Operation): This reference is highly relevant to the low-power operation claims. It describes a device operating in a low-power mode while continuously listening for audio. It also implies a multi-stage process where initial keyword spotting is done with minimal power before engaging further processing. However, it does not appear to disclose the use of "contextual cues" (like motion, location, or time of day) as described in claims 15 and 22. While it discloses a low-power initial processing stage, it does not explicitly detail the use of two distinct processors (a first low-power processor and a second main processor) as recited in claims 29 and 36.

---

2. U.S. Patent Application Publication 2012/0101828 A1: "Always-on Low Power Voice Trigger"

• Full Citation: US 2012/0101828 A1
• Assignee: QUALCOMM Incorporated
• Filing Date: October 21, 2010
• Publication Date: April 26, 2012
• Brief Description: The '828 application describes a method for low-power voice trigger detection. It proposes using a dedicated, low-power hardware component (a "voice trigger circuit" or a low-power DSP) to continuously monitor for a voice trigger phrase. When the phrase is detected, this low-power component wakes up the main application processor to handle the full voice command. This hierarchical approach is explicitly designed to minimize power consumption in an "always-on" listening mode.
• Potential Anticipation of Claims:
  • Claims 1 & 8 (Trigger-less Detection): Similar to the Amazon '327 patent, this application focuses on detecting a "voice trigger phrase," which contradicts the "without requiring receipt of an explicit trigger" limitation of claims 1 and 8.
  • Claims 29 & 36 (Two-Processor System): This reference strongly anticipates the core concept of claims 29 and 36. It discloses a method and system where a first, low-power processor/circuit (Voice Trigger Circuit 104 in its FIG. 1) performs an initial processing stage on acoustic input while the device is in a low-power mode. If a potential trigger is found, a second, more powerful processor (applications processor 102) is engaged for further processing. This directly maps to the two-processor, hierarchical analysis claimed in 29 and 36.
  • Claims 15 & 22 (Low-Power Mode with Context): The '828 application thoroughly describes detecting voice input in a low-power mode using a multi-stage approach. However, it does not appear to disclose the use of additional "contextual cues" (e.g., motion from an accelerometer, GPS location, time of day) to assist in the detection. Its focus is solely on the acoustic properties of the trigger phrase.

---

3. U.S. Patent 9,070,332 B2: "Voice-based device control based on recognized words"

• Full Citation: US 9,070,332 B2
• Assignee: Microsoft Technology Licensing, LLC
• Filing Date: September 15, 2011
• Issue Date: June 30, 2015
• Brief Description: This patent describes a system that listens for speech and attempts to identify command-like phrases even in the absence of a formal "wake word." It discusses parsing natural language utterances to determine if they contain an actionable command by identifying specific keywords or command structures within a stream of speech. The system can operate in a background "listening mode."
• Potential Anticipation of Claims:
  • Claims 1 & 8 (Trigger-less Detection): This reference is highly relevant and potentially anticipates the novelty of claims 1 and 8. It describes a system that can identify a command within general speech "without an explicit user action to transition the electronic device to a command mode" (Abstract, US 9,070,332 B2). This aligns closely with the concept of detecting a command "without requiring receipt of an explicit trigger."
  • Claims 15, 22, 29, 36 (Low-Power & Context/Processor Architecture): While the '332 patent describes a listening mode, it is less specific about the power state and hardware architecture compared to patent 11,087,750. It does not explicitly detail the use of contextual cues (motion, location, etc.) to aid in command detection, nor does it specify the two-processor low-power architecture recited in claims 29 and 36. Its focus is more on the software and natural language processing side of trigger-less command identification.

---

4. U.S. Patent Application Publication 2012/0330663 A1: "Voice Trigger for Electronic Device"

• Full Citation: US 2012/0330663 A1
• Assignee: [Apple Inc.](/litigations/by-plaintiff/Apple%20Inc.)
• Filing Date: June 22, 2011
• Publication Date: December 27, 2012
• Brief Description: This application from Apple discloses a system for recognizing a voice trigger to activate a voice-assistant feature. It describes how a device can use a low-power detection process to listen for a specific trigger phrase (e.g., "Siri"). The application also discusses using contextual information, such as whether the device is being held to the user's ear (using a proximity sensor), to determine whether to activate the voice trigger functionality.
• Potential Anticipation of Claims:
  • Claims 1 & 8 (Trigger-less Detection): This reference teaches the use of an explicit "voice trigger" and therefore does not anticipate claims 1 and 8.
  • Claims 15 & 22 (Low-Power Mode with Context): This reference is highly relevant to claims 15 and 22. It discloses operating in a low-power mode to detect a voice input and explicitly describes using "at least one contextual cue" to assist in the process. For example, it mentions using a proximity sensor to determine device position as a contextual cue for enabling the voice trigger. This aligns directly with the core elements of claims 15 and 22.
  • Claims 29 & 36 (Two-Processor System): The application discusses a "low-power" detection process that can wake a more powerful processor, which is conceptually similar to the two-processor system. However, it is not as explicit as the Qualcomm '828 application in defining two distinct processors for the sequential stages of analysis.

Based on the provided prior art analysis, here is an analysis of the obviousness of the independent claims of U.S. Patent 11,087,750 under 35 U.S.C. § 103.

---

Obviousness Analysis of U.S. Patent 11,087,750

This analysis evaluates whether an invention claimed in US patent 11,087,750 would have been obvious to a "person having ordinary skill in the art" (PHOSITA) at the time the invention was made by combining the teachings of existing prior art references.

Claims 1 & 8: Trigger-less Voice Command Detection

These claims cover the broad method and apparatus for detecting a voice command "without requiring receipt of an explicit trigger."

• Conclusion: These claims are likely rendered obvious by U.S. Patent 9,070,332 B2 (Microsoft '332).
• Reasoning:
  • The Microsoft '332 patent discloses the core novelty of these claims. Its abstract states the system can identify a command within general speech "without an explicit user action to transition the electronic device to a command mode." This directly teaches the limitation of detecting a command "without requiring receipt of an explicit trigger."
  • Microsoft '332 further teaches monitoring an acoustic environment, receiving acoustic input (i.e., a stream of speech), and initiating a response by parsing the speech to determine if it contains an actionable command. This maps directly to all elements of claims 1 and 8.
  • A PHOSITA would find it obvious to apply the method described in Microsoft '332 to a "mobile device," as mobile devices were a primary platform for voice-based user interfaces and command-and-control systems at the time of the invention. Therefore, no combination of references is necessary; Microsoft '332 alone appears to teach all the claimed elements.

Claims 29 & 36: Two-Processor System for Low-Power Detection

These claims cover a method and apparatus for using a first, low-power processor for an initial analysis of acoustic input, followed by a second, higher-power processor for further evaluation if needed, all while the device is in a low-power state.

• Conclusion: These claims are likely rendered obvious by the combination of U.S. Patent Application Publication 2012/0101828 A1 (Qualcomm '828) in view of Microsoft '332.
• Reasoning:
  • What Qualcomm '828 Teaches: Qualcomm '828 explicitly discloses the two-processor architecture for power-efficient voice processing. It teaches a dedicated, low-power hardware component (a "voice trigger circuit" or low-power DSP) that performs a first processing stage (listening for a trigger) while the main "applications processor" remains in a low-power state. Upon detection, the main processor is woken for a second stage of processing. This directly teaches the central limitations of claims 29 and 36: a low-power mode, a first processor for a first stage, and a second processor for a second stage.
  • What is Missing from Qualcomm '828: The Qualcomm system is designed to detect an "explicit trigger" (a specific voice phrase).
  • What Microsoft '332 Teaches: As established above, Microsoft '332 teaches the method of detecting a voice command without an explicit trigger.
  • Motivation to Combine: A PHOSITA would have been motivated to combine the power-saving two-processor architecture of Qualcomm '828 with the more natural, trigger-less interaction method of Microsoft '332. The known problem in the art was balancing "always-on" listening with battery life. Qualcomm '828 provided an elegant hardware solution for power management. Microsoft '332 provided a software solution for a more seamless user experience. A PHOSITA seeking to build a commercially competitive voice-enabled mobile device would have found it obvious to implement the more advanced, trigger-less software from Microsoft '332 on the power-efficient hardware architecture taught by Qualcomm '828. This would have been a predictable combination of a known method with a known system to achieve the known goals of improved usability and extended battery life.

Claims 15 & 22: Low-Power Detection Using Contextual Cues

These claims cover a method and apparatus for detecting a voice command in a low-power mode by using a multi-stage process that is assisted by "at least one contextual cue" (e.g., motion, location, time).

• Conclusion: These claims are likely rendered obvious by the combination of U.S. Patent Application Publication 2012/0330663 A1 (Apple '663) in view of Microsoft '332.
• Reasoning:
  • What Apple '663 Teaches: Apple '663 is highly relevant as it explicitly discloses using "contextual information" to aid in voice detection while in a low-power state. It specifically teaches using a proximity sensor to determine if a device is near the user's ear as a "contextual cue" to enable or disable the voice trigger functionality. This directly teaches the core elements of the claims: operating in a low-power mode, performing detection, and using "at least one contextual cue" to assist.
  • What is Missing from Apple '663: The Apple system uses this context to decide when to listen for an explicit voice trigger (e.g., "Siri").
  • What Microsoft '332 Teaches: Microsoft '332 again supplies the missing element: detecting a command without an explicit trigger.
  • Motivation to Combine: A key challenge for a trigger-less system like that in Microsoft '332 is avoiding false positives—that is, incorrectly identifying background conversation as a command. A PHOSITA would recognize this known problem. Apple '663 provides a clear solution: use contextual cues to make the listening process "smarter" and more selective. A PHOSITA would have been motivated to incorporate the use of contextual cues (as taught by Apple '663) into the trigger-less command detection system (taught by Microsoft '332) to improve its accuracy and reliability. For instance, using an accelerometer to know the device has just been picked up (a contextual cue) would be a logical signal to pay closer attention for a potential command in the subsequent audio stream. This combination would be a commonsense engineering step to improve the performance of a known system.

As of May 8, 2026, the following details pertain to the term, continuity, and family of U.S. Patent 11,087,750.

Patent Term and Expiration

• Patent Term Adjustment (PTA): There is no Patent Term Adjustment (PTA) recorded for this patent. The USPTO's calculation shows 0 days were added due to A, B, or C delays.

• Patent Term Extension (PTE): There is no Patent Term Extension (PTE) recorded for this patent. This type of extension is typically granted for patents covering products that undergo a lengthy regulatory review process (e.g., by the FDA), which is not applicable here.

• Projected Expiration Date: The patent's term is calculated from its earliest non-provisional filing date. Since the application for patent 11,087,750 (US 15/238,238) was filed on August 16, 2016, and there are no prior non-provisional applications in its direct continuity chain, the standard 20-year term applies.

  • Calculation: August 16, 2016 + 20 years = August 16, 2036.

This projected expiration is contingent on the timely payment of all required maintenance fees.

Continuity and Related Applications

U.S. Patent 11,087,750, which issued from application number 15/238,238, is part of a larger family of patents and applications.

• Continuation Applications (Child Applications): The application for this patent (15/238,238) serves as the parent for the following continuation applications:

  • Application No.: 17/397,522 (Filed August 9, 2021)
    • Status: Now U.S. Patent No. 11,676,600 (Issued June 13, 2023)
  • Application No.: 17/867,091 (Filed July 18, 2022)
    • Status: Now U.S. Patent No. 12,548,565 (Issued April 9, 2024)

• Divisional Applications: There are no divisional applications stemming from the application for patent 11,087,750.

• Priority Date: The patent document indicates a priority date of March 12, 2013. This date likely corresponds to an earlier, related provisional application, which establishes the invention date but does not start the 20-year patent term clock. The patent term is calculated from the non-provisional filing date of August 16, 2016.

Patent Family Summary

The patent family related to U.S. Patent 11,087,750 includes the parent patent and its two subsequent continuations, all of which have been granted.

• Parent: U.S. Patent No. 11,087,750
• Continuation 1: U.S. Patent No. 11,676,600
• Continuation 2: U.S. Patent No. 12,548,565

DEFENSIVE DISCLOSURE AND PRIOR ART PUBLICATION

Title: Derivative Methods and Apparatus for Acoustic Command Detection
Publication Date: April 26, 2026
Reference Patent: US 11,087,750 ("the '750 patent")
Description: The following technical disclosures are intended to enter the public domain to be considered prior art for any future patent applications in the field of acoustic command detection, voice processing, and human-computer interaction. These disclosures describe novel extensions, applications, and variations derived from the core concepts taught in US 11,087,750.

---

Part 1: Derivatives of Trigger-less Voice Command Detection (Relates to Claims 1 & 8 of the '750 patent)

Derivative 1.1: Sterile Field Surgical Environment Control

• Axis: Cross-Domain Application (Medical Devices)

• Enabling Description: An apparatus for controlling surgical equipment (e.g., endoscopic cameras, cauterization tools, information displays) via trigger-less voice commands within a sterile operating room. The system utilizes an array of directional, far-field microphones focused on the lead surgeon. The acoustic models are specifically trained to distinguish command phrases from normal intra-operative conversation and medical terminology using semantic analysis. The system rejects any acoustic input originating from outside a pre-defined "sterile zone" around the operating table, using time-delay-of-arrival (TDOA) calculations from the microphone array for source localization. The command grammar is constrained to prevent accidental activation of critical equipment; for instance, a command to increase power to a cauterization device would require a two-part command structure with a confirmation phrase.

  graph TD
      subgraph Operating Room
          A[Mic Array] -->|Acoustic Stream| B(Signal Processor);
          B -->|Source Localization| C{Sterile Zone?};
          C -->|Yes| D[Semantic Command Classifier];
          C -->|No| E[Discard];
          D -->|Valid Command| F(Surgical Device Interface);
          F --> G[Endoscope Control];
          F --> H[Display Control];
      end
  

Derivative 1.2: Predictive Intent Command Initiation using Edge AI

• Axis: Integration with Emerging Tech (AI)

• Enabling Description: A method wherein a mobile device uses a generative large language model (LLM) running on an edge AI accelerator (e.g., a Neural Processing Unit) to predict user intent and pre-stage a response before a voice command is fully articulated. The system analyzes the initial phonemes of an utterance in conjunction with a rich set of contextual cues (see Part 2). For example, if the user picks up the phone (motion cue) at 6:00 PM (time cue) near their home (location cue) and utters "Wha-," the system predicts a high probability of the query "What's the traffic like on my way home?" It then pre-fetches traffic data from a server. If the user completes the predicted command, the response is delivered instantly. If the command diverges, the pre-fetched data is discarded and the actual command is processed. This reduces perceived latency.

  sequenceDiagram
      actor User
      participant Device
      participant Edge_AI_NPU
      participant Server
  
      User->>+Device: Speaks "Wha..."
      Device->>Edge_AI_NPU: Phonemes + Context Cues
      Edge_AI_NPU-->>Device: Predicts "What's traffic?" (Prob: 0.85)
      Device->>+Server: Pre-fetch traffic data
      Server-->>-Device: Traffic data
      User->>Device: Finishes command: "...t's the traffic?"
      Device-->>-User: Instantly displays traffic data
  

Derivative 1.3: Infrasonic Industrial Machinery Control

• Axis: Operational Parameter Expansion (Frequency)

• Enabling Description: A method for detecting voice commands in extreme-noise industrial environments (e.g., stamping plants, engine rooms) by transposing human speech into the infrasonic frequency range (1-20 Hz). The user speaks into a noise-canceling microphone headset, which modulates the speech onto an infrasonic carrier wave transmitted via a dedicated transducer. A receiver on the industrial controller is tuned to this infrasonic channel, which is significantly below the frequency spectrum of ambient machine noise. The receiver demodulates the signal back into an audible frequency for processing by the voice command detection engine. This effectively isolates the command signal from environmental noise interference.

  graph TD
      A[User Speech] --> B(Noise-Canceling Mic);
      B --> C(Infrasonic Modulator);
      C --> D((Transducer));
      subgraph High-Noise Environment
          D -- Infrasonic Wave (5 Hz) --> E((Receiver));
      end
      E --> F(Infrasonic Demodulator);
      F --> G(Voice Command Processor);
      G --> H[Machine Control Unit];
  

Derivative 1.4: Bone-Conducted Command Detection via Piezoelectric Sensors

• Axis: Material & Component Substitution

• Enabling Description: A system that replaces microphones with an array of piezoelectric film sensors integrated into the chassis of a wearable device (e.g., smart glasses, helmet). These sensors detect voice commands as mechanical vibrations conducted through the user's skull (bone conduction). The system processes these vibration signatures instead of acoustic waves. This method is immune to high levels of ambient airborne noise and is effective for covert operations or when the user is wearing breathing apparatus. The processing unit uses a machine learning model trained on the unique spectral patterns of bone-conducted vibrations, which differ from airborne acoustics.

  stateDiagram-v2
      [*] --> Idle
      Idle --> Listening: Vibration Detected
      Listening --> Processing: Vibration pattern matches command signature
      Processing --> Executing: Command validated
      Executing --> Idle: Task complete
      Processing --> Idle: Invalid command
      Listening --> Idle: No command signature
  

Derivative 1.5: Contextual Command Muting ("Acoustic Cloaking")

• Axis: The "Inverse" or Failure Mode

• Enabling Description: A method for intelligently disabling trigger-less command detection based on contextual cues indicating a high probability that any detected speech is not intended for the device. The system integrates with the user's calendar, GPS, and ambient audio analysis. If the device detects it is in a location tagged as "Movie Theater" or an event on the calendar is marked "Confidential Meeting," it enters a "Muted" state, ignoring all voice input. Furthermore, if the system's VAD detects multiple distinct speakers in a short time frame (indicating a conversation), it will temporarily lower the confidence threshold required to initiate a command, effectively requiring a more explicit and clear utterance to activate.

  flowchart LR
      A[Acoustic Input] --> B{Context Check};
      subgraph Context Sources
          C[Calendar]
          D[GPS Location]
          E[Multi-Speaker VAD]
      end
      C & D & E --> B;
      B -- Context is Private/Public --> F[Enter Muted State];
      F --> G[Ignore Input];
      B -- Context is Permissive --> H[Process Input Normally];
  

---

Part 2: Derivatives of Low-Power Detection with Contextual Cues (Relates to Claims 15 & 22 of the '750 patent)

Derivative 2.1: Hyper-Contextual IoT Sensor Fusion

• Axis: Integration with Emerging Tech (IoT)

• Enabling Description: A method where the mobile device acts as a central command unit, fusing contextual data from a distributed network of low-power IoT sensors via a mesh protocol (e.g., Thread, Zigbee). These sensors provide real-time data on room occupancy (PIR sensors), ambient light levels, temperature, air pressure, and even specific device states (e.g., a smart TV is on). This hyper-contextual data stream is used to dynamically adjust the acoustic processing pipeline. For example, if occupancy sensors indicate the user is alone and the TV is off, the system uses a highly sensitive acoustic model. If multiple people are present and the TV is on, it switches to a noise-robust model and uses TDOA to focus only on the device owner's voiceprint.

  classDiagram
      MobileDevice {
          +processAcousticInput(audio)
          -activeAcousticModel
          -updateContext(contextData)
      }
      IoTSensor <|-- PIRSensor
      IoTSensor <|-- LightSensor
      IoTSensor <|-- TVStateSensor
      MobileDevice o-- "many" IoTSensor : Fuses data from
      class IoTSensor{
          <<interface>>
          +readData()
      }
  

Derivative 2.2: Livestock Biometric and Environmental Monitoring

• Axis: Cross-Domain Application (AgTech)

• Enabling Description: A system for monitoring livestock health where an animal-worn sensor package (e.g., an ear tag or collar) uses the principles of low-power contextual detection. The device remains in a sleep state, conserving power. It is activated by a combination of acoustic and contextual cues. For example, it wakes upon detecting a specific vocalization pattern (acoustic cue) that co-occurs with a sudden spike in body temperature and a drop in motion (contextual cues from integrated biometric sensors). This event could signify distress. Upon waking, the device records a longer audio snippet and transmits it, along with the contextual data, to a central farm management system for analysis by a veterinarian.

  stateDiagram-v2
      state "Low-Power Sleep" as Sleep
      state "Active Monitoring" as Active
      [*] --> Sleep
      Sleep --> Active: (Acoustic Distress) AND (High Temp) AND (Low Motion)
      Active --> Transmitting: Data packet compiled
      Transmitting --> Sleep: Transmission complete
      Active --> Sleep: Timeout / False Trigger
  

Derivative 2.3: Multi-Source Energy Harvesting for Contextual Sensors

• Axis: Material & Component Substitution

• Enabling Description: A mobile device where the low-power processor and its associated contextual sensors (accelerometer, GPS, etc.) are powered independently from the main battery by a dedicated multi-source energy harvesting module. This module comprises a photovoltaic film on the device's surface, a piezoelectric generator to convert kinetic energy from motion, and an RF energy harvester to capture power from ambient Wi-Fi and cellular signals. A power management IC (PMIC) selects the optimal energy source or combines sources to charge a supercapacitor. This ensures that the "always-on" contextual awareness function can operate indefinitely without draining the main battery, only drawing from it when the main processor must be engaged.

  graph TD
      subgraph Energy Sources
          A[Photovoltaic Film]
          B[Piezoelectric Generator]
          C[RF Harvester]
      end
      subgraph Power Management
          A & B & C --> D[PMIC];
          D --> E[Supercapacitor];
      end
      subgraph Low-Power Domain
          E --> F(Low-Power CPU);
          F --> G[Context Sensors];
      end
      H[Main Battery] --> I(Main CPU);
      F -- Wake-up signal --> I;
  

---

Part 3: Derivatives of Two-Processor System Architecture (Relates to Claims 29 & 36 of the '750 patent)

Derivative 3.1: Neuromorphic First-Stage "Cochlea" Processor

• Axis: Component Substitution

• Enabling Description: An apparatus where the first, low-power processor is a neuromorphic spiking neural network (SNN) chip designed to mimic the function of the human cochlea. This processor receives the raw microphone data and converts it into a sparse, event-based stream of neural spikes. It is exceptionally power-efficient for continuous monitoring. It performs rudimentary voice activity detection and phoneme classification. Only when the spike patterns indicate a high probability of human speech with command-like intonation does it wake the second processor, a conventional CPU, and passes the recognized phoneme stream (not the raw audio) for full speech recognition and natural language understanding.

  sequenceDiagram
      participant Mic
      participant Neuromorphic_SNN
      participant Main_CPU
      Mic->>+Neuromorphic_SNN: Continuous Audio Waveform
      loop Always-On Low-Power
          Neuromorphic_SNN->>Neuromorphic_SNN: Processes audio into spikes
      end
      Neuromorphic_SNN->>Main_CPU: Wake-up + Phoneme Stream
      activate Main_CPU
      Main_CPU->>Main_CPU: ASR and NLU
      Main_CPU-->>-Neuromorphic_SNN: Return to sleep
      deactivate Main_CPU
  

Derivative 3.2: Blockchain-Verified Command Handoff

• Axis: Integration with Emerging Tech (Blockchain)

• Enabling Description: A method for high-security applications where the two-processor system creates an immutable, non-repudiable record of commands. The first low-power processor detects a potential voice command and a voiceprint from the user. It generates a hash of the preliminary acoustic features and the user's voiceprint. Upon waking the second, more powerful processor, it passes this hash along with the full acoustic data. The second processor performs full command recognition and, upon successful execution, writes a transaction to a private blockchain. The transaction includes the initial hash, the final recognized command text, a timestamp, and is cryptographically signed using a key stored in a secure enclave. This creates a verifiable audit trail for commands used in financial transactions or physical access control.

  flowchart TD
      A[Acoustic Input] --> B(Low-Power Processor);
      B --> C[Extract Voiceprint + Acoustic Features];
      C --> D[Generate Hash_1];
      D --> E{Wake Main Processor?};
      E -- Yes --> F(Main Processor);
      B -- Acoustic Data --> F;
      D -- Hash_1 --> F;
      F --> G[Full ASR + NLU];
      G --> H{Execute Command};
      H -- Success --> I[Create Blockchain Transaction];
      I -- (Hash_1, Command Text, Timestamp) --> J((Private Ledger));
  

Derivative 3.3: Distributed Asynchronous Processing for Aerospace

• Axis: Cross-Domain Application (Aerospace)

• Enabling Description: In an aircraft cockpit, the "first processor" is a network of simple, redundant Digital Signal Processors (DSPs), each connected to a microphone in a different location (e.g., pilot's helmet, co-pilot's headset, ambient cabin). These DSPs perform noise cancellation and VAD locally. The "second processor" is a centralized, fault-tolerant flight control computer. When any DSP detects speech, it transmits a compressed feature vector to the central computer. The central computer uses inputs from multiple DSPs to triangulate the speaker's location and identity, fuse the feature vectors to improve recognition accuracy in high-G and high-vibration environments, and validate the command against the current flight state before execution.

  graph TD
      subgraph Distributed DSPs (First Processor Stage)
          DSP1[Pilot Mic DSP]
          DSP2[Co-Pilot Mic DSP]
          DSP3[Cabin Mic DSP]
      end
      subgraph Central Computer (Second Processor Stage)
          FC[Flight Control Computer]
      end
      DSP1 -- Feature Vector --> FC
      DSP2 -- Feature Vector --> FC
      DSP3 -- Feature Vector --> FC
      FC -->|Fuse Data & Validate| EXEC[Execute Flight Command]
  

---

Part 4: Combination Prior Art with Open-Source Standards

1. Combination with RISC-V and TensorFlow Lite: A mobile device is disclosed wherein the first, low-power processor (as in claim 29) is implemented as a custom System-on-Chip (SoC) utilizing the open-source RISC-V instruction set architecture. The core is specifically designed with custom instructions to accelerate the matrix multiplication and convolution operations common in audio feature extraction (e.g., MFCCs). The voice activity detection (VAD) and limited keyword spotting models running on this processor are built and optimized using the open-source TensorFlow Lite for Microcontrollers framework. This allows for a fully open-source, highly-optimized hardware/software stack for the first stage of acoustic processing, minimizing power and licensing costs.

2. Combination with Matter Protocol for IoT Control: The trigger-less voice command detection system (as in claim 1) is integrated as a feature in a smart home hub. When the system detects a command like "It's too dark in the living room," the NLU module on the hub's main processor interprets the intent. It then translates this intent into a standardized command using the open-source Matter application layer protocol. It sends a "LevelControl: MoveToLevel" command to the Zigbee/Thread address of the lighting group designated as "living room," demonstrating a seamless integration of natural language voice control with an open smart home standard.

3. Combination with the ONNX (Open Neural Network Exchange) Standard: A method is disclosed where the acoustic models used for voice command detection (both on the low-power and main processors) are stored and deployed using the open-source ONNX format. This decouples the model training pipeline from the specific hardware inference engine. Models can be trained in any popular framework (e.g., PyTorch, JAX) and exported to ONNX. The device's runtime environment can then use an ONNX-compatible inference engine (e.g., ONNX Runtime) that is optimized for its specific silicon (e.g., a Qualcomm Hexagon DSP or an Apple Neural Engine), allowing for flexible and portable deployment of state-of-the-art acoustic models without vendor lock-in.