A voice processing method, device, equipment and storage medium
By generating the filter coefficient before receiving the wake-up word at the terminal and filtering the voice data, the problem of unable to effectively filter out voice data noise in the prior art is solved, and efficient voice processing in a noisy environment is realized.
CN114333877BActive Publication Date: 2025-03-25SOUNDAI TECH CO LTD
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202111564679.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-12-20
- Publication Date
- 2025-03-25
- Estimated Expiration
- 2041-12-20
AI Technical Summary
Technical Problem
Existing speech processing methods cannot effectively filter out noise in speech data, especially in noisy environments.
Method used
By generating the filter coefficient before receiving the wake-up word at the terminal, the received voice data is filtered to ensure that the filter coefficient is not affected by the wake-up word pronunciation, thereby effectively filtering out noise.
Benefits of technology
It realizes effective filtering of voice data in a noisy environment, improving the accuracy of speech recognition and the effectiveness of filtering.
✦ Generated by Eureka AI based on patent content.
Abstract
The embodiments of the present application disclose a voice processing method, device, equipment and storage medium. The method includes: receiving first voice data, the first voice data is received after the terminal switches from the standby state to the working state, and includes voice data of instruction information; based on the first filter coefficient generated by the terminal at the first moment, the first voice data is filtered to obtain the voice data of the instruction information, the first moment is the moment before the wake-up word is received, and the wake-up word is used to instruct the terminal to switch from the standby state to the working state. The method provided in the embodiments of the present application can effectively filter out noise in the voice data.
Need to check novelty before this filing date? Find Prior Art