Speech Audio Characteristics
Audio can be encoded at different sampling rates (i.e. samples per second – the most common being: 8, 16, 32, 44.1, 48, and 96 kHz), and different bits per sample (the most common being: 8-bits, 16-bits or 32-bits). Speech recognition engines work best if the acoustic model they use was trained with speech audio which was recorded at the same sampling rate/bits per sample as the speech being recognized.
Read more about this topic: Acoustic Model
Famous quotes containing the word speech:
“If we should swap a good library for a second-rate stump speech and not ask for boot, it would be thoroughly in tune with our hearts. For deep within each of us lies politics. It is our football, baseball, and tennis rolled into one. We enjoy it; we will hitch up and drive for miles in order to hear and applaud the vitriolic phrases of a candidate we have already reckoned we’ll vote against.”
—Federal Writers’ Project Of The Wor, U.S. public relief program (1935-1943)