20240029757. Linear Prediction Residual Energy Tilt-Based Audio Signal Classification Method and Apparatus simplified abstract (HUAWEI TECHNOLOGIES CO., LTD.)
Contents
Linear Prediction Residual Energy Tilt-Based Audio Signal Classification Method and Apparatus
Organization Name
Inventor(s)
Linear Prediction Residual Energy Tilt-Based Audio Signal Classification Method and Apparatus - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240029757 titled 'Linear Prediction Residual Energy Tilt-Based Audio Signal Classification Method and Apparatus
Simplified Explanation
The audio signal classification method described in the patent application involves determining the voice activity of a current audio frame. Based on this determination, the method decides whether to obtain and store the frequency spectrum fluctuation of the current audio frame in a memory. The method also updates the stored frequency spectrum fluctuations based on whether the audio frame is percussive music or activity from a historical audio frame. Finally, the method classifies the current audio frame as either a speech frame or a music frame by analyzing the statistics of the frequency spectrum fluctuations stored in the memory.
- The method determines the voice activity of a current audio frame.
- It decides whether to store the frequency spectrum fluctuation of the current audio frame based on the voice activity.
- The method updates the stored frequency spectrum fluctuations based on the type of audio frame.
- It classifies the current audio frame as speech or music by analyzing the statistics of the stored frequency spectrum fluctuations.
Potential Applications:
- Speech recognition systems can benefit from accurate classification of speech frames.
- Music analysis and recognition systems can benefit from accurate classification of music frames.
- Audio processing applications can use this method to separate speech and music frames for further processing.
Problems Solved:
- Accurate classification of speech and music frames in audio signals.
- Efficient storage and updating of frequency spectrum fluctuations for classification purposes.
Benefits:
- Improved accuracy in speech and music classification.
- Enhanced performance of speech recognition and music analysis systems.
- Efficient utilization of memory for storing frequency spectrum fluctuations.
Original Abstract Submitted
an audio signal classification method includes determining, according to voice activity of a current audio frame, whether to obtain a frequency spectrum fluctuation of the current audio frame and store the frequency spectrum fluctuation in a frequency spectrum fluctuation memory, and updating, according to whether the audio frame is percussive music or activity of a historical audio frame, frequency spectrum fluctuations stored in the frequency spectrum fluctuation memory, and classifying the current audio frame as a speech frame or a music frame according to statistics of a part or all of effective data of the frequency spectrum fluctuations stored in the frequency spectrum fluctuation memory.
