Adaptive frame skipping for speech recognition
By using adaptive frame skipping technology in the speech recognition system, the feature vectors of audio frames are compared to determine whether to skip processing, which solves the problem of high power consumption of normally open speech recognition engines, and realizes power saving and system resource optimization.
CN119768861APending Publication Date: 2025-04-04QUALCOMM INC
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202380060434.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-08-26
- Filing Date
- 2023-07-07
- Publication Date
- 2025-04-04
AI Technical Summary
Technical Problem
Mobile electronic devices and IoT devices consume a high power supply for normally open voice recognition engines, resulting in a shortened battery life and waste of system resources.
Method used
Adaptive frame skipping technology is adopted to compare the feature vectors of audio frames, and determine whether to skip the processing of feature vectors, reducing dependence on neural network models and saving processing energy.
Benefits of technology
It effectively reduces the power consumption during voice recognition, extends the battery life of the device, and optimizes the utilization of system resources.
✦ Generated by Eureka AI based on patent content.
Abstract
Systems and techniques for processing audio signals are described herein. For example, a process may include receiving a first audio frame associated with a first time frame. The process may also include generating a first time frame feature vector based on the first audio frame. The process may include determining a distance between a first time frame feature vector and a second time frame feature vector. A second time frame feature vector may be generated based on a second audio frame associated with a second time frame, wherein the second time frame precedes the first time frame. The process may also include comparing a distance between the first time frame feature vector and the second time frame feature vector to a threshold distance. The process may include determining whether to skip processing of the first audio frame by the application based on the comparison.
Need to check novelty before this filing date? Find Prior Art