| ID | 原文 | 译文 |
| 53717 | 基于矢量量化变分自编码器( Vector Quantized Variational Autoencoder，VQVAE) 的语音转换系统是国内外语音转换领域研究的一大热点，但是其较差的转换音质限制了模型的应用。 | The vector quantized variational autoencoder ( VQVAE) based voice conversion system is a hot spot in voice conversion area, but the poor quality of converted speeches limits its wide use. |
| 53718 | 本文在 VQVAE 的基础上提出一种改进的矢量量化正则变分自编码器 ( Vector Quantization Ｒegularized Variational Autoencoder，VQ- ＲEG-VAE) 。 | To address this problem, this paper proposes an improved model called vector quantization regularized variational autoencoder ( VQ-ＲEG-VAE) . |
| 53719 | 在训练时，矢量量化退化为正则化项， | During training, vector quantization works as the regularization term. |
| 53720 | 通过矢量量化的正则约束让编码器学习生成说话人无关的语义特征，同时让解码器学习将说话人特征融合到语义特征中。 | Through the regularization of vector quantization, the encoder learns to generate speaker-independent linguistic features while the decoder learns to fuse the speaker features into linguistic fea- tures. |
| 53721 | 在转换时，可以去掉矢量量化这一正则化项，通过编码器和解码器就能实现语音转换。 | During conversion, voice conversion can be realized through the encoder and the decoder. |
| 53722 | 由于转换时没有进行矢量量化，语义特征信息得以更好保留。 | Since vector quantization is not used during the conversion, more linguitic information can be preserved. |
| 53723 | 客观和主观实验都表明:基于 VQ-ＲEG-VAE 模型的转换语音在不降低相似度的前提下，音质比 VQVAE 模型有显著的提升。 | The objective and subjective experiments have shown that, compared with VQVAE model, VQ-ＲEG-VAE model achieved significant improvement in speech quality and comparable results in speaker similarity. |
| 53724 | 在信源数目未知的欠定盲源分离问题中，精确地估计混合矩阵是具有挑战性的问题。 | In underdetermined blind source separation with unknown number of sources, it is challenging to estimate themixing matrix precisely. |
| 53725 | 针对现有方法在病态条件下( 某些混合向量的方向接近) 不能准确估计信源数目、易受离群点干扰的不足，提出了一种基于方向性模糊 C-means 与 K-means 的混合矩阵估计方法。 | Two major shortcomings of existing methods are that they cannot estimate the number of sourcescorrectly under ill-conditioned conditions ( namely, the directions of some mixed vectors are close) and they are susceptibleto outliers. To deal with these issues, a mixing matrix estimation method based on directional fuzzy C-means ( DFCM) andK-means is proposed. |
| 53726 | 该方法首先通过方向性模糊 C-means 对观测信号进行预聚类，通过预聚类可以实现: | First, the observation signals are pre-clustered by DFCM, such that we can: |