A speech communication apparatus of the present invention includes, in addition to an echo canceller for canceling an acoustic echo generated in a hands-free speech space, a chirp signal generating unit and a training unit. The chirp signal generating unit generates a chirp signal adequate for initial training of the echo canceller. The training control unit enables the chirp signal generating unit to generate a chirp signal, when a predetermined condition for starting hands-free speaking is satisfied, and a chirp tone corresponding to the chirp signal to be output as a volume-amplified tone from the hands-free speaker. The echo canceller performs initial training of the echo canceller based on the chirp tone.