Speech Extraction of a Target Speaker from One Mixed Speech Signal

スポンサーリンク

概要

• 論文の詳細を見る

• This paper proposes a method of speech extraction of a target speaker from one mixed speech signal of some speakers. The proposed method uses a dictionary consisted of feature vectors of a speech signal. The feature vectors are spectra of a segment of the speech signal which contains all phonemes. The dictionary is made in advance from a clear speech signal of the target speaker, and is employed in extracting the target speech signal from one mixed speech signal. The effectiveness of the proposed method has been verified by computer simulations.

• The Institute of Electrical Engineers of Japanの論文

著者

• Suetake Noriaki

  Department Of Physics And Information Sciences Yamaguchi University

• Uchino Eiji

  Department Of Physics And Information Science Faculty Of Science. Yamaguchi University

• Uchino Eiji

  Department of Physics, Biology and Informatics, Yamaguchi University

• Azetsu Tadahiro

  Department of Environmental Design, Yamaguchi Prefectural University

関連論文

• 2 Comprehensive Multifactorial Approach to Plaque Vulnerability Using a Novel Modality of Intravascular Imaging(Vulnerable Patient/Vulnerable Plaque in Acute Coronary Syndrome,Plenary Session 2 (PL-2) (H),The 73rd Annual Scientific Meeting of The Japanese
• PJ-712 Tissue Classification of Plaque Considering Spatial Continuity of Components by Using Intravascular Ultrasound and Its Color-coded 3D Imaging(Intravascular endoscopy / Intravascular ultrasound(07)(I),Poster Session(Japanese),The 72nd Annual Scienti
• 1 Seeking New Era of Atherosclerotic Plaque Imaging : An Attempt to Develop a Hybrid IVUS-OCT System(Symposium 13 (SY-13) (I) Freshscent Forefront in Atherosclerotic Plaque Imagings,Special Program,The 72nd Annual Scientific Meeting of the Japanese Circul
• 1 Comprehensive Approach for Identifying Vulnerable Coronary Plaques with Use of Intravascular Ultrasound(New Horizon in Coronary Interventions for Acute Coronary Syndrome, The 71st Annual Scientific Meeting of the Japanese Circulation Society)
• Dynamic Deletion of Units for Self-Organizing Map by Introducing a New Measure of Unit's Contribution to Learning (論文特集:自己組織化マップとその応用)
• Separability-Based Intelligent Scissors for Interactive Image Segmentation(Advanced Image Technology)
• Speech Extraction of a Target Speaker from One Mixed Speech Signal

スポンサーリンク