Improving singing aid system for laryngectomees with statistical voice conversion and VAE-space

Li Li, Tomoki Toda, Kazuho Morikawa, Kazuhiro Kobayashi, Shoji Makino

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

This paper proposes an improved singing aid system for laryngectomees that converts electrolaryngeal (EL) speech produced using an electrolarynx to a more naturally sounding singing voice. Although the previously proposed system employing a noise suppression process and a rulebased pitch control approach has achieved preliminary success in converting EL speech into a singing voice, there are still two major limitations. First, the converted singing voice still sounds mechanical and unnatural owing to the adverse impacts of spectrograms extracted from EL speeches, also making the effect of pitch control limited. Second, the capability and flexibility of the rulebased pitch control in modeling various singing styles are insufficient, causing the converted singing voices to lack variety. To address these limitations, this paper proposes an improved system that uses 1) a statistical voice conversion approach to convert spectrograms extracted from EL speeches into those of natural speeches and 2) a deep generative model-based approach called VAE-SPACE for pitch modification, which generates pitch patterns in a data-driven manner instead of following manually designed rules. The experimental results revealed that 1) the conversion of spectrograms was effective in improving the naturalness of singing voices, and 2) the statistical pitch control approach was able to achieve comparable results with the rule-based approach, which was very carefully designed to be specialized in singing.

本文言語English
ホスト出版物のタイトルProceedings of the 20th International Society for Music Information Retrieval Conference, ISMIR 2019
編集者Arthur Flexer, Geoffroy Peeters, Julian Urbano, Anja Volk
出版社International Society for Music Information Retrieval
ページ784-790
ページ数7
ISBN(電子版)9781732729919
出版ステータスPublished - 2019
外部発表はい
イベント20th International Society for Music Information Retrieval Conference, ISMIR 2019 - Delft, Netherlands
継続期間: 2019 11 42019 11 8

出版物シリーズ

名前Proceedings of the 20th International Society for Music Information Retrieval Conference, ISMIR 2019

Conference

Conference20th International Society for Music Information Retrieval Conference, ISMIR 2019
国/地域Netherlands
CityDelft
Period19/11/419/11/8

ASJC Scopus subject areas

  • 音楽
  • 情報システム

フィンガープリント

「Improving singing aid system for laryngectomees with statistical voice conversion and VAE-space」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル