The training of the tone of Mandarin two-syllable words based on pitch projection synthesis speech

Summary form only given. This paper uses pitch projection method to synthesize teaching speech by selecting the appropriate standard voice. To synthesize the teaching speech, lexicon tones in learners' speech is turned into standard tones, while keeping the segments and timbie unchanged. Thereby complex variation of speech signal is reduced except for tone. Then the paper carries tone training experiments for Japanese based on the synthesis speech of Mandarin two-syllable words. The training results show that the method of synthesis speech is superior to standard voice method in relative improvement of perception, production, as well as generalization of production. The method of synthesis speech is far better than the method of control group without training. Most of the results are statistically significant. Experimental results also prove the existence of selective attention mechanism of the human brain when learning speech. It provides an experimental and theoretical basis that speech synthesis method could be integrated into the computer-assisted Mandarin tone learning system.