Speech morphing by gradually changing spectrum parameter and fundamental frequency
نویسنده
چکیده
This paper proposes a new application of speech modi cation 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 multi-media entertainment together with image morphing. The proposed algorithm pitch-synchronously modi es fundamental frequency(F0) and DFT spectrum and outputs high quality speech. To clarify the balance of F0 modi cation and spectrum modi cation, listening tests were carried out using 20 male speakers. The results yielded the relationship between the amount of modi cation and speaker identity. In terms of overall performance, listening tests show that the proposed algorithm successfully generates smooth, high quality voice changes.
منابع مشابه
Unsupervised Speech Morphing between Utterances of any Speakers
A new approach to speech morphing is presented which avoids the extraction of fundamental and formant frequencies as well as the detection of phone or syllable boundaries. All prominent spectral and temporal features of the source and target utterances are automatically related and interpolated. The method consists of three main parts: LPC-based source-filter decomposition, separate interpolati...
متن کاملGradually changing expression of singing voice based on morphing
We have developed a method for synthesizing a singing voice by gradually changing the musical expression based on speech morphing. This paper shows the advantages of this method in comparison with the approach of binary discrete transformation between two expressions, confirmed by statistical analyses of perception tests. In order to synthesize different expressional strengths of a singing voic...
متن کاملStudy on manipulation method of voice quality based on the vocal tract area function
This paper describes a new manipulation method of voice quality which is based on the STRAIGHT analysis-synthesis system. This method manipulates voice quality by changing the vocal tract area function calculated from the PARCOR coefficients. The PARCOR coefficients used in the proposed method is obtained from the auto-correlation function of the STRAIGHT spectrum. We have implemented a simple ...
متن کاملAutomatic assignment of anchoring point correspondence between time-frequency r
The automatic assignment of anchoring points is proposed to define the correspondence between the timefrequency representations of speech samples for speech morphing, speech texture mapping, and so on. The correspondence is modeled as a set of segmental bilinear function. These model parameters are called anchoring points. Although, the correspondence significantly affects the quality of such m...
متن کاملبررسی برخی ویژگی های آکوستیک گفتار نوزاد مدار در مادران فارسی زبان
Introduction: When adults talk to another person, linguistic characteristics of the listener will also be considered. A clear example of speech changes depending on the listener is maternal or infant directed speech. Infant directed speech is more slowly with longer sentences and pauses at the end of the utterance. Undoubtedly the most distinctive feature of this style of speech is acoustic c...
متن کامل