9th ISCA Workshop on Speech Synthesis Workshop (SSW 9) 2016
DOI: 10.21437/ssw.2016-11
|View full text |Cite
|
Sign up to set email alerts
|

Development of a statistical parametric synthesis system for operatic singing in German

Abstract: In this paper we describe the development of a Hidden Markov Model (HMM) based synthesis system for operatic singing in German, which is an extension of the HMM-based synthesis system for popular songs in Japanese and English called "Sinsy". The implementation of this system consists of German text analysis, lexicon and Letter-To-Sound (LTS) conversion, and syllable duplication, which enables us to convert a German MusicXML input into context-dependent labels for acoustic modelling. Using the front-end, we dev… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2018
2018
2023
2023

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(1 citation statement)
references
References 7 publications
0
1
0
Order By: Relevance
“…This in contrast to deep learning approaches, which can jointly model timbre and F0 from a set of natural songs. Other machine learning approaches, such as those based on Hidden Markov Models (HMMs) (Saino et al, 2006;Oura et al, 2010;Nakamura et al, 2014;Pucher et al, 2016;Li & Wang, 2016), offer similar flexibility in this aspect, but tend to have other drawbacks. Notably, HMM-based methods tend to have a series of limitations inherent to the model itself, such as modeling each phoneme as a small number of discrete states with constant statistics, and many others.…”
Section: Singing Synthesismentioning
confidence: 99%
“…This in contrast to deep learning approaches, which can jointly model timbre and F0 from a set of natural songs. Other machine learning approaches, such as those based on Hidden Markov Models (HMMs) (Saino et al, 2006;Oura et al, 2010;Nakamura et al, 2014;Pucher et al, 2016;Li & Wang, 2016), offer similar flexibility in this aspect, but tend to have other drawbacks. Notably, HMM-based methods tend to have a series of limitations inherent to the model itself, such as modeling each phoneme as a small number of discrete states with constant statistics, and many others.…”
Section: Singing Synthesismentioning
confidence: 99%