Real-Time Contrast Enhancement to Improve Speech Recognition
Figure 2
Simulated input to the WTA network.
(a) Unenhanced spatiotemporal signal. (b) WTA enhanced spatiotemporal signal demonstrating spectral sharpening and expansion of the position of the spectral peaks as a consequence of dynamic competition between subband channels. (c) Cross-section of channels at 150 ms for unenhanced signals (blue), dynamically enhanced (red), and instantaneously enhanced (black) spatiotemporal signals illustrating spatial (spectral) sharpening. (d) Cross-section of channels at 370 ms for unenhanced (blue), dynamically enhanced (red), and instantaneously enhanced (black) spatiotemporal signals illustrating sharpening and expansion of spectral peaks.