Speech morphing by gradually changing spectrum parameter and fundamental frequency
暂无分享,去创建一个
The paper proposes a new application of speech modification called "speech morphing". In image processing, morphing is a well known technique that gradually changes one person's face to that of someone else. Speech morphing produces similar results for speech; i.e., one person's speech is gradually changed to that of someone else. Speech morphing makes it possible to create movies or multimedia entertainment together with image morphing. The proposed algorithm pitch-synchronously modifies fundamental frequency (F/sub 0/) and DFT spectrum and outputs high quality speech. To clarify the balance of F/sub 0/ modification and spectrum modification, listening tests were carried out using 20 male speakers. The results yielded the relationship between the amount of modification and speaker identity. In terms of overall performance, listening tests show that the proposed algorithm successfully generates smooth, high quality voice changes.
[1] Eric Moulines,et al. A diphone synthesis system based on time-domain prosodic modifications of speech , 1989, International Conference on Acoustics, Speech, and Signal Processing,.
[2] Chikio Hayashi. On the quantification of qualitative data from the mathematico-statistical point of view , 1950 .