Mixture of factor analyzers using priors from non-parallel speech for voice conversion

• المؤلفون الرئيسيون: Wu, Zhizheng, Kinnunen, Tomi, Chng, Eng Siong, Li, Haizhou
• مؤلفون آخرون: School of Computer Engineering
• التنسيق: مقال
• اللغة: English
• منشور في: 2013
• الموضوعات: DRNTU::Engineering::Computer science and engineering
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/102726; http://hdl.handle.net/10220/16436
• المؤسسة: Nanyang Technological University

A robust voice conversion function relies on a large amount of parallel training data, which is difficult to collect in practice. To tackle the sparse parallel training data problem in voice conversion, this paper describes a mixture of factor analyzers method which integrates prior knowledge from non-parallel speech into the training of conversion function. The experiments on CMU ARCTIC corpus show that the proposed method improves the quality and similarity of converted speech. With both objective and subjective evaluations, we show the proposed method outperforms the baseline GMM method.