Automatic system and method for analysing content of audio signals
A technology of audio and audio signals, which is applied in the general search field and can solve problems such as not considering audio event indexing
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach
[0104] Proceeding to block 162, the dominant frequency for each sample is determined. During the determination of the dominant frequency, the preferred embodiment of the invention considers the following 8 frequency bands:
[0105] R1-100 Hz to 3,000 Hz R2-3,000 Hz to 4,000 Hz
[0106] R3-4,000 Hz to 5,000 Hz R4-5,000 Hz to 6,000 Hz
[0107] R5-6,000 Hz to 6,500 Hz R6-6,500 Hz to 7,000 Hz
[0108] R7 - 7,000 Hz to 7,500 Hz R8 - 7,500 Hz to 8,000 Hz
[0109] For each sample, the dominant frequency is calculated as follows:
[0110] R n Freq = number of frequencies in the nth band, n = 1 to 8, divided by the total number of samples, where the main frequency range is defined as R n The largest value among the Freq values (8).
[0111] Moving to block 164, a histogram is used to normalize the dominant frequencies. Having determined and normalized the dominant frequency of the audio stream samples, the process moves to block 166 to identify samples whose dominant frequency...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 