Singing voice synthesis - a research on the effects of dynamic time warping, a speech recognition method on speech-to-singing synthesis
Singing Voice Synthesis has been researched on and developed extensively for 50 years and beyond. Till date, many research studies have been to produce operatic singing voices, using practical approaches such as Vocal Tract Length Normalisation (VTLN) and other methods of synthesis. Singing Voice Sy...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2012
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/50132 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Singing Voice Synthesis has been researched on and developed extensively for 50 years and beyond. Till date, many research studies have been to produce operatic singing voices, using practical approaches such as Vocal Tract Length Normalisation (VTLN) and other methods of synthesis. Singing Voice Synthesis involves the controlling of the three acoustic features unique to singing voices, namely the fundamental frequency (F0), phoneme duration, and spectrum. Through extracting these features into which of a set of classes, it helps to develop the diversity and functionality of the application. |
|---|