%Aigaion2 BibTeX export from Idiap Publications
%Thursday 21 November 2024 04:46:59 PM

@TECHREPORT{Saheer_Idiap-RR-31-2015,
         author = {Saheer, Lakshmi and Na, Xingyu and Cernak, Milos},
       projects = {Idiap, DBOX},
          month = {10},
          title = {Syllabic Pitch Tuning for Neutral-to-Emotional Voice Conversion},
           type = {Idiap-RR},
         number = {Idiap-RR-31-2015},
           year = {2015},
    institution = {Idiap},
       abstract = {Prosody plays an important role in both identification and synthesis of emotionalized speech. Prosodic features like pitch are usually estimated and altered at a segmental level based on short windows of speech (where the signal is expected to be quasi-stationary). This results in a frame-wise change of acoustical parameters for synthesizing emotionalized speech. In order to convert a neutral speech to an emotional speech from the same user, it might be better to alter the pitch parameters at the  suprasegmental level like at the syllable-level since the changes in the signal are more subtle and smooth. In this paper we aim to show that the pitch transformation in a neutral-to-emotional voice
conversion system may result in a better speech quality output if the transformations are performed at the supra-segmental (syllable) level rather than a frame-level change. Subjective evaluation results are shown to demonstrate if the naturalness, speaker similarity and the emotion recognition tasks show any performance difference.},
            pdf = {https://publications.idiap.ch/attachments/reports/2015/Saheer_Idiap-RR-31-2015.pdf}
}