Google llc (20240242728). Cascade Architecture for Noise-Robust Keyword Spotting simplified abstract
Contents
Cascade Architecture for Noise-Robust Keyword Spotting
Organization Name
Inventor(s)
Yiteng Huang of Mountain View CA (US)
Alexander H. Gruenstein of Mountain View CA (US)
Cascade Architecture for Noise-Robust Keyword Spotting - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240242728 titled 'Cascade Architecture for Noise-Robust Keyword Spotting
The abstract of this patent application describes a method that involves receiving multi-channel audio captured by an array of microphones on a user device, processing the audio to detect a hotword, and then cleaning the audio data to generate a clean monophonic audio chomp for further processing.
- Receiving multi-channel audio captured by an array of microphones on a user device
- Processing the audio using a first stage hotword detector to determine if a hotword is detected
- Providing chomped raw audio data to a second processor for noise cleaning
- Generating a clean monophonic audio chomp using a first noise cleaning algorithm
- Processing the clean monophonic audio chomp using a second stage hotword detector to detect the hotword
Potential Applications: - Voice-controlled devices - Speech recognition systems - Smart home automation - Virtual assistants
Problems Solved: - Efficient hotword detection in noisy environments - Improved audio processing for accurate speech recognition - Enhancing user experience with voice-activated technology
Benefits: - Enhanced accuracy in detecting hotwords - Improved performance in noisy conditions - Seamless integration with existing voice recognition systems
Commercial Applications: Title: Advanced Hotword Detection Technology for Voice-Controlled Devices This technology can be utilized in smart speakers, smartphones, automotive infotainment systems, and other IoT devices to enhance user interaction and improve overall functionality.
Prior Art: Prior research in hotword detection algorithms and noise reduction techniques in audio processing can provide valuable insights into the development of this technology.
Frequently Updated Research: Researchers are constantly exploring new algorithms and techniques to improve hotword detection accuracy and noise reduction in audio processing. Stay updated on the latest advancements in this field to enhance the performance of voice-controlled devices.
Questions about Hotword Detection Technology: 1. How does this technology improve the accuracy of hotword detection in noisy environments? 2. What are the key differences between the first stage and second stage hotword detectors in this method?
Original Abstract Submitted
a method includes receiving, at a first processor of a user device, streaming multi-channel audio captured by an array of microphones, each channel including respective audio features. for each channel, the method also includes processing, by the first processor, using a first stage hotword detector, the respective audio features to determine whether a hotword is detected. when the first stage hotword detector detects the hotword, the method also includes the first processor providing chomped raw audio data to a second processor that processes, using a first noise cleaning algorithm, the chomped raw audio data to generate a clean monophonic audio chomp. the method also includes processing, by the second processor using a second stage hotword detector, the clean monophonic audio chomp to detect the hotword.
