Parameterless-Growing-SOM and Its Application to a Voice Instruction Learning System

Figure 4

An instruction (sit down) features input to robot in different languages. Left$:$ sound waves; right: normalized features in 20-dimentional space.

(a) Japanese$:$ Osuwari (sit down)

(b) English$:$ Sit (sit down)

(c) Chinese$:$ Zuoxia (sit down)

(d) Malaysian$:$ Duduk (sit down)