I have two video where two person having conversation. They begin recording different times. I want to match these two videos' frame numbers, i.e. By matching audio.
How can I do that?
Asked
Active
Viewed 51 times
0
-
Look up audio alignment and see, for example, A Probabilistic Model Based Approach For Aligning Multiple Audio Sequences – Emre Jul 18 '15 at 05:02
1 Answers
1
The problem you want to solve is called automatic audio alignment, or auto-synchronization of audio. Common algorithms are phase correlation, cross correlation on the raw audio waveform. People also use more "cooked" audio features like MFCCs, say each 10ms frame, and measure frame-wise similarity between the audio segments to be compared.
There are many threads on Stack overflow that show how to do this. For example: find-short-clip-of-audio-within-longer-clip-of-audio, cross-correlation-vs-fft-for-finding-phase-between-2-signals. Also some interesting repos on github, audiosync, videosync
ruoho ruotsi
- 1,770
- 9
- 10