{"id":233,"date":"2022-12-11T06:32:11","date_gmt":"2022-12-11T06:32:11","guid":{"rendered":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/f22-teamb2\/?p=233"},"modified":"2022-12-11T06:32:11","modified_gmt":"2022-12-11T06:32:11","slug":"marcos-status-report-12-10-2022","status":"publish","type":"post","link":"http:\/\/course.ece.cmu.edu\/~ece500\/projects\/f22-teamb2\/2022\/12\/11\/marcos-status-report-12-10-2022\/","title":{"rendered":"Marco’s Status Report 12\/10\/2022"},"content":{"rendered":"

This week, I finished implementing the audio reconstruction pipeline which allows us to listen to the audio being extracted by the SDFT bins.<\/p>\n

As a reminder, my goal was to take an original audio of someones voice (see first audio sample below), and the extract the frequencies present in a user’s voice that correspond to the frequencies of piano keys. However, we’d have no idea if we’re extracting enough information by only using the power present at the piano key frequencies \u2014 therefore we needed to somehow reconstruct an audio file using the frequencies we picked up.<\/p>\n

\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
I generated the reconstructed audio by multiplying the reconstructed samples with an exponential decay function so that the frequencies could be sustained for long enough like they would be on a piano.<\/div>\n
<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
\n
The first image is the original audio, the second image uses the exponential function y=Ae^((-0.001)x), and the third image uses the exponential decay function y=Ae^((-0.0001)x). Below each image is it’s corresponding audio.<\/div>\n
<\/div>\n
Please lower you’re computer volume before playing the following recordings, they are a bit choppy.<\/div>\n
<\/div>\n<\/div>\n
Original Audio<\/strong><\/div>\n
\n
<\/div>\n
\"\"<\/div>\n
\n\n