Laughing voice recognition using periodic waveforms and voice-likeness features
Taisuke Sakano, Takahiro Kigawa, Masanori Sugimoto, Fusako Kusunoki, Shigenori Inagaki, Hiroshi Mizoguchi · 2016
With a goal of advancing human-machine collaboration, we propose a method to recognize a laughing voice. A previous study that proposed a laughing voice recognition method was based on the periodic waveform feature of the laughing voice. However, identifying laughing voices from waveforms is problematic, because this can result in false positive results. To overcome this problem, we propose a laughing voice recognition method that incorporates a voice-likeness feature. In addition, we make a laughing voice recognition system using our proposed method. To confirm the efficacy of the laughing voice recognition method, we evaluated this system. In our evaluation, we were able to correctly recognize laughing voice at a high success rate of 97%. In comparison with the previous study, the recognition rate improved by 18%; therefore, our proposed method can be considered an effective in recognizing laughing voice.