Prior art — US Patent 11087750

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.
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.