To provide acoustic information of affective speech for computer modelling, this study conducted an investigation on the friendly Mandarin Chinese speech. Based on the perceptually classified friendly and neutral speech data, spectral, tonal and durational analyses were conducted at different phonetic levels. The distinctive acoustic features of friendly speech were sifted out and followed by tentative discussions.
By: Fanxin Chen, Aijun Li, Haibo Wang, Tianqing Wang, Qiang Fang
Published in: Proceedings of 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.Piscataway, NJ, , IEEE. , vol.1, p.I569-72 in 2004
Please obtain a copy of this paper from your local library. IBM cannot distribute this paper externally.
Questions about this service can be mailed to reports@us.ibm.com .