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...

Full description

Bibliographic Details
Main Author: Ng, Wan Ling.
Other Authors: Ong Keng Sian, Vincent
Format: Final Year Project (FYP)
Language:English
Published: 2012
Subjects:
Online Access:http://hdl.handle.net/10356/50132
_version_ 1826116466144968704
author Ng, Wan Ling.
author2 Ong Keng Sian, Vincent
author_facet Ong Keng Sian, Vincent
Ng, Wan Ling.
author_sort Ng, Wan Ling.
collection NTU
description 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.
first_indexed 2024-10-01T04:12:11Z
format Final Year Project (FYP)
id ntu-10356/50132
institution Nanyang Technological University
language English
last_indexed 2024-10-01T04:12:11Z
publishDate 2012
record_format dspace
spelling ntu-10356/501322023-07-07T16:43:48Z Singing voice synthesis - a research on the effects of dynamic time warping, a speech recognition method on speech-to-singing synthesis Ng, Wan Ling. Ong Keng Sian, Vincent School of Electrical and Electronic Engineering DRNTU::Engineering::Electrical and electronic engineering 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. Bachelor of Engineering 2012-05-30T03:45:27Z 2012-05-30T03:45:27Z 2012 2012 Final Year Project (FYP) http://hdl.handle.net/10356/50132 en Nanyang Technological University 91 p. application/pdf
spellingShingle DRNTU::Engineering::Electrical and electronic engineering
Ng, Wan Ling.
Singing voice synthesis - a research on the effects of dynamic time warping, a speech recognition method on speech-to-singing synthesis
title Singing voice synthesis - a research on the effects of dynamic time warping, a speech recognition method on speech-to-singing synthesis
title_full Singing voice synthesis - a research on the effects of dynamic time warping, a speech recognition method on speech-to-singing synthesis
title_fullStr Singing voice synthesis - a research on the effects of dynamic time warping, a speech recognition method on speech-to-singing synthesis
title_full_unstemmed Singing voice synthesis - a research on the effects of dynamic time warping, a speech recognition method on speech-to-singing synthesis
title_short Singing voice synthesis - a research on the effects of dynamic time warping, a speech recognition method on speech-to-singing synthesis
title_sort singing voice synthesis a research on the effects of dynamic time warping a speech recognition method on speech to singing synthesis
topic DRNTU::Engineering::Electrical and electronic engineering
url http://hdl.handle.net/10356/50132
work_keys_str_mv AT ngwanling singingvoicesynthesisaresearchontheeffectsofdynamictimewarpingaspeechrecognitionmethodonspeechtosingingsynthesis