メインナビゲーションにスキップ 検索にスキップ メインコンテンツにスキップ

Generative Moment Matching Network-based Random Modulation Post-filter for DNN-based Singing Voice Synthesis and Neural Double-tracking

研究成果: Conference contribution

7   !!Link opens in a new tab 被引用数 (Scopus)

抄録

This paper proposes a generative moment matching network (GMMN)-based post-filter that provides inter-utterance pitch variation for deep neural network (DNN)-based singing voice synthesis. The natural pitch variation of a human singing voice leads to a richer musical experience and is used in double-tracking, a recording method in which two performances of the same phrase are recorded and mixed to create a richer, layered sound. However, singing voices synthesized using conventional DNN-based methods never vary because the synthesis process is deterministic and only one waveform is synthesized from one musical score. To address this problem, we use a GMMN to model the variation of the modulation spectrum of the pitch contour of natural singing voices and add a randomized inter-utterance variation to the pitch contour generated by conventional DNN-based singing voice synthesis. Experimental evaluations suggest that 1) our approach can provide perceptible inter-utterance pitch variation while preserving speech quality. We extend our approach to double-tracking, and the evaluation demonstrates that 2) GMMN-based neural double-tracking is perceptually closer to natural double-tracking than conventional signal processing-based artificial double-tracking is.

本文言語English
ホスト出版物のタイトル2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ページ7070-7074
ページ数5
ISBN(電子版)9781479981311
DOI
出版ステータスPublished - 2019 5月
外部発表はい
イベント44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
継続期間: 2019 5月 12 → 2019 5月 17

出版物シリーズ

名前ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
巻2019-May
ISSN(印刷版)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
国/地域United Kingdom
CityBrighton
Period19/5/12 → 19/5/17

ASJC Scopus subject areas

  • ソフトウェア
  • 信号処理
  • 電子工学および電気工学

フィンガープリント

「Generative Moment Matching Network-based Random Modulation Post-filter for DNN-based Singing Voice Synthesis and Neural Double-tracking」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