By utilizing the fact that speaker identity and content vary on different time scales, \acrlong{fhvae} (\acrshort{fhvae}) uses a sequential latent variable and a segmental latent variable to symbolize these two attributes. Disentanglement is carried out by assuming the latent variables representing speaker and content follow sequence-dependent and sequence-independent priors. For the sequence-dependent prior, \acrshort{fhvae} assumes a Gaussian distribution with an utterance-scale varying mean and a fixed small variance. The training process promotes sequential variables getting close to the mean of its prior with small variance. However, this constraint is relatively weak. Therefore, we introduce contrastive learning in the \acrshort{fhvae} framework. The proposed method aims to make the sequential variables clustering when representing the same speaker, while distancing themselves as far as possible from those of other speakers. The structure of the framework has not been changed in the proposed method but only the training process, thus no more cost is needed during test. Voice conversion has been chosen as the application in this paper. Latent variable evaluations include speakerincrease verification and identification for the sequential latent variable, and speech recognition for the segmental latent variable. Furthermore, assessments of voice conversion performance are on the grounds of speaker verification and speech recognition experiments. Experiment results show that the proposed method improves both sequential and segmental feature extraction compared with \acrshort{fhvae}, and moderately improved voice conversion performance.
翻译:使用演讲人身份和内容在不同时间尺度上不同的事实, \ acrlong{fhvae} (\ acrshort{fhvae}) 使用一个连续潜伏变量和一个区块潜伏变量来象征这两个属性。 通过假设代表演讲人和内容的潜伏变量以顺序为依附于和顺序为依存的前题, 进行分解。 对于先前取决于顺序的前题, \ acrshort{fhvae} 假设一个高斯分布, 表达比例不同, 平均和固定的微小差异。 培训过程促进顺序变量接近其先前的中位值, 且有小的变换。 但是, 这一限制相对较弱。 因此, 我们在\ acrshort{fvae} 框架中引入对比性学习, 代表演讲人和内容根据顺序排列的组合, 尽量让自己与其他演讲人保持距离。 在拟议方法中, 框架的结构没有改变, 但只有培训过程, 因此试验期间不需要增加费用。 语音转换已被选择为用于 用于 不断变动的演讲人的递增变换的演示结果 。 和变变变变的演变的演示的演的演算法,, 显示的演变的演变的演算法, 和变的演化的演化的演算法 显示的演化, 和变的演化, 显示的演化的演化的演化的演变的演算法 显示的演算法 显示的演算法的演算法的演算法, 显示的演算法的演算法 显示的演化, 和演算法的演算法的演变法的演变法的演变法的演化的演化的演进法的演化的演化的演化法的演化法的演算法的演法的演法的演算法的演法的演化方法是的演算法的演化法的演化法的演化法的演化法的演化法的演化法的演化法的演化法的演算法的演算法的演化法的演化法的演化法的演化的演化法的演化法的演化法的演化的演化的演