音频检测的方法、设备和存储介质
By performing frame-by-frame processing and energy difference analysis on audio signals, and combining the frequency and energy average of the fundamental tone and overtones, the problem of not being able to accurately distinguish between true voice and false voice in existing technologies has been solved, thus improving the accuracy of audio detection and the effects of sound correction and scoring.
CN116564349BActive Publication Date: 2026-07-17TENCENT MUSIC ENTERTAINMENT TECH (SHENZHEN) CO LTD
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TENCENT MUSIC ENTERTAINMENT TECH (SHENZHEN) CO LTD
- Filing Date
- 2023-05-16
- Publication Date
- 2026-07-17
Smart Images
Figure CN116564349B_ABST
Abstract
本公开提供了一种音频检测的方法、设备和存储介质，属于音频技术领域。所述方法包括：对待检测音频进行分帧处理，得到多帧音频信号；对于每帧音频信号，确定所述音频信号在目标频段对应的能量；根据所述音频信号在目标频段对应的能量和所述音频信号之前的N帧音频信号在所述目标频段分别对应的能量，确定所述音频信号的演唱类型，其中，演唱类型为真声演唱或者假声演唱，N为正整数。本公开可以实现对音频信号是真声演唱还是假声演唱的判断。
Need to check novelty before this filing date? Find Prior Art