采用联合字典优化的噪声鲁棒性语音转换算法

针对含噪语音难以实现有效的语音转换,本文提出了一种采用联合字典优化的噪声鲁棒性语音转换算法。在联合字典的构成中,语音字典采用后向剔除算法(Backward Elimination algorithm,BE)进行优化,同时引入噪声字典,使得含噪语音与联合字典相匹配。实验结果表明,在保证转换效果的前提下,后向剔除算法能够减少字典帧数,降低计算量。在低信噪比和多种噪声环境下,本文算法与传统NMF算法和基于谱减法消噪的NMF转换算法相比具有更好的转换效果,噪声字典的引入提升了语音转换系统的噪声鲁棒性。 

A noise robust voice conversion algorithm based on joint dictionary optimization

A noise robust voice conversion algorithm based on joint dictionary optimization is proposed in this paper to solve the problem that it is difficult to effectively convert noisy source speech into the target one.In the composition of the joint dictionary,the speech dictionary is optimized using a backward elimination algorithm.At the same time,a noise dictionary is introduced to match the noisy speech with the joint dictionary.The experimental results show that the backward elimination algorithm can decrease the number of dictionary frames and reduce the amount of calculation while ensuring the conversion effect.In low SNR and multiple noise environments,the algorithm has better conversion effect than the traditional NMF algorithm and the NMF conversion algorithm plus spectral subtraction de-noising.The proposed algorithm improves the robustness of the voice conversion system.