18307736. Decaying Automated Speech Recognition Processing Results simplified abstract (Google LLC)

From WikiPatents
Jump to navigation Jump to search

Decaying Automated Speech Recognition Processing Results

Organization Name

Google LLC

Inventor(s)

Matthew Sharifi of Kitchberg (CH)

Victor Carbune of Zürich (CH)

Decaying Automated Speech Recognition Processing Results - A simplified explanation of the abstract

This abstract first appeared for US patent application 18307736 titled 'Decaying Automated Speech Recognition Processing Results

Simplified Explanation

The abstract describes a method for decaying speech processing in a voice-enabled device. When a microphone trigger event is detected, the device opens the microphone to capture speech for speech recognition. The captured audio stream is then provided to a speech recognition system, with the level of speech recognition processing decaying over time based on the duration window.

  • Receiving indication of a microphone trigger event
  • Instructing the microphone to open and capture audio stream
  • Providing the audio stream to a speech recognition system
  • Decaying the level of speech recognition processing over time

Potential Applications

This technology can be applied in various voice-enabled devices such as smart speakers, virtual assistants, and voice-controlled appliances.

Problems Solved

1. Efficient speech processing: By decaying the level of speech recognition processing over time, the device can optimize resources and improve efficiency. 2. Privacy concerns: Opening the microphone only when necessary for speech recognition helps address privacy concerns related to constant audio capture.

Benefits

1. Improved user experience: By capturing speech more efficiently, the device can provide faster and more accurate responses to user commands. 2. Resource optimization: Decaying speech processing helps conserve device resources and prolong battery life.

Potential Commercial Applications

"Optimizing Speech Processing in Voice-Enabled Devices"

Possible Prior Art

There may be prior art related to speech recognition systems that optimize processing based on the duration of audio capture.

Unanswered Questions

How does this technology impact the accuracy of speech recognition over time?

The abstract mentions decaying the level of speech recognition processing, but it does not specify how this decay affects the accuracy of speech recognition results.

What measures are in place to ensure user privacy when the microphone is open for audio capture?

While the abstract mentions opening the microphone for a duration window, it does not detail any specific privacy measures implemented during this process.


Original Abstract Submitted

A method for decaying speech processing includes receiving, at a voice-enabled device, an indication of a microphone trigger event indicating a possible interaction with the device through speech where the device has a microphone that, when open, is configured to capture speech for speech recognition. In response to receiving the indication of the microphone trigger event, the method also includes instructing the microphone to open or remain open for a duration window to capture an audio stream in an environment of the device and providing the audio stream captured by the open microphone to a speech recognition system. During the duration window, the method further includes decaying a level of the speech recognition processing based on a function of the duration window and instructing the speech recognition system to use the decayed level of speech recognition processing over the audio stream captured by the open microphone.