this is for an application in which passwords are stored in the form of audio inputs . In order to provide user access , the password(in audio form) will be matched with already stored password(audio only) in the database . I wanted to know how to measure the extent of similarity in two audio patterns . the audio patterns can be a clap sequence , knock sequence , whistle etc
Asked
Active
Viewed 1,667 times
2 Answers
2
Look up acoustic fingerprint or audio fingerprinting and dynamic-time warping for some basic technologies used to compare audio files.
hotpaw2
- 35,346
- 9
- 47
- 90
1
You could also take a look at pattern recognition in the time-frequency domain. This would imply to take the entire audio signal and perform time-frequency analysis (finding a pro version of the spectrogram) and analize that as an image. If the two time-frequency representations match for the audio files, it is very likely that they are the same password.
bone
- 1,241
- 11
- 15