The present invention provides a method for recovering target speech based on shapes of amplitude distributions of split spectra obtained by use of blind signal separation. This method includes: a first step of receiving target speech emitted from a sound source and a noise emitted from another sound source and forming mixed signals of the target speech and the noise at a first microphone and at a second microphone; a second step of performing the Fourier transform of the mixed signals from the time domain to the frequency domain, decomposing the mixed signals into two separated signals U1 and U2 by use of the Independent Component Analysis, and, based on transmission path characteristics of the four different paths from the two sound sources to the first and second microphones, generating the split spectra v11, v12, v21 and v22 from the separated signals U1 and U2; and a third step of extracting estimated spectra Z* corresponding to the target speech to generate a recovered spectrum group of the target speech, wherein the split spectra v11, v12, v21, and v22 are analyzed by applying criteria based on the shape of the amplitude distribution of each of the split spectra v11, v12, v21, and v22, and performing the inverse Fourier transform of the recovered spectrum group from the frequency domain to the time domain to recover the target speech.