Reproduction of speech feedback mechanism in an anthropomorphic talking robot

We reproduced the feedback mechanism of human speech for an anthropomorphic talking robot WT-5 (Waseda Talker No. 5). The Waseda Talker series mimics human speech organs such as the vocal cords, tongue and lips, and WT-5 could produce various vowels and consonant sounds. We elucidate the mechanisms of human speech and speech acquisition using this robot. In human speech acquisition, humans build phoneme categories through mimic speaking. In mimic speaking, infants reproduce adult voices by a feedback mechanism. We have developed a vowel mimic speaking mechanism using auditory feedback that optimized sound pressure and the first and second formants (F1, F2). We also developed consonant mimic speaking using sensory information such as tactile and pressure sensors. Moreover, we developed consonant mimic speaking by auditory feedback. In the feedback mechanism, we constructed acoustic features from MFCCs (MelFrequency Cepstral Coefficients). Supported by a Grant-in-Aid for Scientific Research (A), 16200015 from MEXT, Japan.

[1]  Mitsuhiro Nakamura,et al.  Mechanical voice system and its singing performance , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[2]  Atsuo Takanishi,et al.  Development of a New Human-like Talking Robot for Human Vocal Mimicry , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[3]  J. Flanagan.  Speech Analysis, Synthesis and Perception , 1971 .

[4]  Martin Riches,et al.  MOTORMOUTH A Speaking Machine , 1998 .

[5]  Atsuo Takanishi,et al.  Mimicry of human speech sounds using an anthropomorphic talking robot by auditory feedback , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[6]  Masaaki Honda,et al.  Compensatory responses of articulators to unexpected perturbation of the palate shape , 2002, J. Phonetics.