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.
I am trying to identify a specific sound – a baseball being hit with a bat. I have measured the hertz of a number of recordings of a ball being hit and established a relatively reliable hertz range for the hits. I was hoping to use the hertz range within which the recorded sounds fall to identify a hit recorded by the microphone. This generally works well, but certain sounds like a whistle do fall within the same range. How can I identify specific sounds more reliably?
In addition to frequency, your program could evaluate the amplitude (envelope) over time. If a sound is one second, then it would not qualify. If its attack is too slow, it would not qualify.
Beyond the base frequency, you can detect/match fluctuation to frequency as well as timbre/harmonics.