Fast locally linear embedding algorithm for exemplar-based voice conversion

The locally linear embedding (LLE) algorithm has been proven to have high output quality and applicability for voice conversion (VC) tasks. However, the major shortcoming of the LLE-based VC approach is the time complexity (especially in the matrix inversion process) during the conversion phase. In...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:APSIPA ASC 2017 : proceedings, ninth Asia-Pacific Signal and Information Processing Association Annual Summit and Conference : 12-15 December 2017, Kuala Lumpur, Malaysia s. 591 - 595
Hlavní autoři: Peng, Yu-Huai, Hsu, Chin-Cheng, Wu, Yi-Chiao, Hwang, Hsin-Te, Liu, Yi-Wen, Tsao, Yu, Wang, Hsin-Min
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.12.2017
Témata:
Clustering algorithms
Dictionaries
Feature extraction
Manifolds
Speech
Time complexity
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The locally linear embedding (LLE) algorithm has been proven to have high output quality and applicability for voice conversion (VC) tasks. However, the major shortcoming of the LLE-based VC approach is the time complexity (especially in the matrix inversion process) during the conversion phase. In this paper, we propose a fast version of the LLE algorithm that significantly reduces the complexity. In the proposed method, each locally linear patch on the data manifold is described by a pre-computed cluster of exemplars, and thus the major part of on-line computation can be carried out beforehand in the off-line phase. Experimental results demonstrate that the VC performance of the proposed fast LLE algorithm is comparable to that of the original LLE algorithm and that a real-time VC system becomes possible because of the highly reduced time complexity.
DOI:10.1109/APSIPA.2017.8282112