Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.
Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
guys. I am currently doing a project to detect which environment(e.g. on car,on bus, on trains, on street, in canteens,) are you in based on the audio recorded in that environment.
Basically I will record a wav first, and do FFT, and analyze on the frequency domain.
The software should be developed as an Android app.
I have read papers about HMM, MFCC, but I believe they are too complicated for just detecting a few environment.
Any idea or suggestion is welcomed! Thanks in advance
I have been working on a similar project several years ago, and trying to know the users current vehicle from the information collected from multiple sensors like accelerometer, gyroscope and GPS.
In that project, i used FFT, decision tree and HMM. I think only audio + FFT is far not enough, FFT can extract several features on frequency domain from audio data, but only these cannot distinguish the environment.
My suggestion is choosing a proper algorithm in data mining to train a strong model, and use HMM or other methods to do time series analysis.