Lin, C.-Y., Roger Jang, J.-S.: Automatic Phonetic Segmentation by Score Predictive Model for the Corpora of Mandarin Singing Voices. In: The Second IEEE Pacific-Rim Conference on Multimedia, Beijing, China (October 2001) Jang, J.-S.R., Lee, H.-R., Yeh, C.-H.: Query by Tapping: A New Paradigm for Content-based Music Retrieval from Acoustic Input. In: The 13th ACM Multimedia Conference (Poster paper, acceptance rate 17%), Berkeley, CA, USA (November 2003) Lin, C.-Y., Jang, J.-S.R., Hsu, M.-Y.: An Automatic Singing Voice Rectifier. In: The 13th ACM Multimedia Conference (Demo paper), Berkeley, CA, USA (November 2003) Jang, J.-S.R., Jang, Y.-S.: Micro-controller Implementation of Melody Recognition. (eds.) Current Directions in Computer Music Research, pp. Keywordsīennett, G., Rodet, X.: Synthesis of the singing voice. From the subjective listening test, the MOS (mean opinion score) of 3.3 and 3.2 are obtained for the synthesized singing voices and the similarity of singer’s voice, respectively. The synthesized singing voice sounds reasonably good. Moreover, the energy, duration, and spectrum modifications are also implemented in the mixed unit. The third one is the mixed unit which has some undesirable artificial-sounding buzzy-effects, including echo and vibrato effects. The second one is the modified unit and it is employed to implement the pitch-shifting function using the PSOLA method. The first one is the input unit which allows the user specifies a musical score and phonetically-spelled lyrics to system. ![]() This system is designed based on 3 units. ![]() ![]() The system can receive the continuous speech of the lyrics of a song, and can synthesize the intended song based on the MIDI-based music database. This paper presents useful techniques and considerations in implementing underlying mandarin singing voice synthesis system using the RSLI unit.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |