Speech Recording
Speech Recording
In this exercise, you are to record yourself saying yes and no. We will use these recordings for later assignments. Your recordings should be at 8000 samples per second. You can create your recordings using a computer or other digital recording device (some mp3 players have a recording function). In case it is not available in the operating system, there are many utilities for both MS and Mac systems. For example, Audacity is a free recording and audio editing software system for both Mac and MS. 1. Audacity: a free audio recorder and editor for both MS and Mac systems. http://audacity.sourceforge.net/ 2. recorder.xhead 5.0 a very simple recorder for the Mac. http://www.xheadsoftware.com/recorder_xhead.asp 3. Audio Recorder 3.2 a very simple recorder for the Mac. http://www.versiontracker.com/dyn/moreinfo/macosx/17392 Using the recording utility, you should create a wav le; most utilities can export to a wav le. You should then read the wav into MATLAB using the wavread command. Using MATLAB, you should form one vector of 4000 samples (half second) for the yes. You should form a second vector also of 4000 samples of the no. You should export these vectors with the MATLAB command save. You should end up with two .mat les; one le for yes and one le for no. Note that the recording you originally make does not need to be a half second in duration; you can trim the signal down to 4000 samples after you read the signal into MATLAB. To turn in: Plots of your two speech signals (like below). To verify that your .mat les work correctly, you can use the following commands to listen to the audio and plot the signal. >> clear >> load yes_file.mat >> whos Name Size Bytes Class yes 4000x1 32000 double array Grand total is 4000 elements using 32000 bytes >> >> >> >> fs = 8000; % sampling rate soundsc(yes, fs); plot((1:4000)/fs, yes) xlabel(TIME (SECONDS))
Everyones signal will be dierent. To give you a sense of what you might get, my data is shown in the gure.
YES 1 0.5 0 0.5 1 0 0.05 0.1 0.15 0.2 0.25 0.3 TIME (SECONDS) NO 0.35 0.4 0.45 0.5
1 0.5 0 0.5 1 0 0.05 0.1 0.15 0.2 0.25 0.3 TIME (SECONDS) 0.35 0.4 0.45 0.5