scholarly journals Singing Voice Conversion with Disentangled Representations of Singer and Vocal Technique Using Variational Autoencoders

Author(s):  
Yin-Jyun Luo ◽  
Chin-Cheng Hsu ◽  
Kat Agres ◽  
Dorien Herremans
Author(s):  
Stephanie Vander Wel

This chapter offers new insights about the musical and cultural significance of singing styles in country music by contextualizing the details of predominant female vocal approaches within the rich and complex history of southern vernacular singing and by considering, the role of the performing body in relation to the singing voice. Specifically, it takes into account the vocal techniques of Loretta Lynn in relation to the musical conventions of honky tonk singing, the physiological and bodily components of vocal production, and the role of microphone and recording technology. With a chest-dominant vocal technique—amplified by the microphone—Lynn has projected a vocal identity of strength and conviction interpreted as the first working-class feminist voice in country music. This chapter demonstrates that singers such as Kitty Wells, Jean Shepard, and Rose Maddox helped to forge a distinct singing style that had a lasting influence on Lynn’s vocal performances.


2016 ◽  
Vol E99.D (11) ◽  
pp. 2767-2777
Author(s):  
Kazuhiro KOBAYASHI ◽  
Tomoki TODA ◽  
Tomoyasu NAKANO ◽  
Masataka GOTO ◽  
Satoshi NAKAMURA

2020 ◽  
Author(s):  
Liqiang Zhang ◽  
Chengzhu Yu ◽  
Heng Lu ◽  
Chao Weng ◽  
Chunlei Zhang ◽  
...  

2018 ◽  
Vol 201 ◽  
pp. 02006
Author(s):  
Hung-Che Shen

This work reports development of a MIDI-to-Singing song synthesis that will produce audio files from MIDI data and arbitrary Romaji lyrics in Japanese. The MIDI-to-Singing system relies on the Flinger (Festival singer) for singing voice synthesis. Originally, this MIDI-to-Singing system was developed by English. Based on some Japanese pronunciation rules, a Japanese MIDI-to-Sing synthesis system was developed and derived. For a language transfer like Festival synthesized singing, two major tasks are the modifications of a phoneset and a lexicon. Originally, MIDI-to-Sing song synthesis can create singing voices in many languages, but there is no existing Japanese festival diphone voice available right now. We therefore used a voice transformation model in festival to develop Japanese MIDI-to-Singing synthesis. An evaluation of a song listening experiment was conducted and the result of this voice conversion showed that the synthesized singing voice successfully migrate from English to Japanese with high voice quality.


Author(s):  
Kazuhiro Kobayashi ◽  
Tomoki Toda ◽  
Tomoyasu Nakano ◽  
Masataka Goto ◽  
Graham Neubig ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document