Exemplar-Based Voice Conversion Using Sparse Representation in Noisy Environments

• TAKASHIMA Ryoichi

  Graduate School of System Informatics, Kobe University

• TAKIGUCHI Tetsuya

  Graduate School of System Informatics, Kobe University

• ARIKI Yasuo

  Graduate School of System Informatics, Kobe University

抄録

This paper presents a voice conversion (VC) technique for noisy environments, where parallel exemplars are introduced to encode the source speech signal and synthesize the target speech signal. The parallel exemplars (dictionary) consist of the source exemplars and target exemplars, having the same texts uttered by the source and target speakers. The input source signal is decomposed into the source exemplars, noise exemplars and their weights (activities). Then, by using the weights of the source exemplars, the converted signal is constructed from the target exemplars. We carried out speaker conversion tasks using clean speech data and noise-added speech data. The effectiveness of this method was confirmed by comparing its effectiveness with that of a conventional Gaussian Mixture Model (GMM)-based method.

収録刊行物

• IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

  IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences E96.A (10), 1946-1953, 2013

  一般社団法人 電子情報通信学会

キーワード

• voice conversion
• exemplar-based
• sparse coding
• non-negative matrix factorization
• noise robustness

詳細情報

• CRID: 1390001206310793088
• NII論文ID: 130004519150
• DOI: 10.1587/transfun.e96.a.1946
• ISSN: 17451337
• ISSN: 09168508
• Web Site: https://www.jstage.jst.go.jp/article/transfun/E96.A/10/E96.A_1946/_pdf
• 本文言語コード: en
• データソース種別:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用不可