用协方差矩阵提升说话人识别，性能比传统方法高15.5%。
SoCov: Semi-Orthogonal Parametric Pooling of Covariance Matrix for Speaker Recognition
- 用自注意力特征计算协方差矩阵，再通过半正交参数化压缩成向量。
- 在SRE21测试集上，等错误率（EER）相对降低15.5%。
- 适合追求高精度说话人识别的工程与研究场景。
传统深度说话人嵌入框架中，池化层对帧级特征进行均值和标准差统计，生成固定长度表示。该方法忽略帧间协方差信息且等权处理所有帧。本文提出半正交参数化协方差矩阵池化（SoCov），从自注意力帧级特征中计算协方差矩阵，并通过半正交参数化向量化压缩，再与加权标准差向量拼接，作为段级层输入。基于SoCov的深度嵌入称为sc-vector。在SRE21开发集与评估集上的实验表明，sc-vector系统显著优于传统x-vector，SRE21Eval上相对降低15.5% EER；使用自注意力特征时，相比传统均值+标准差统计，相对减少约30.9% EER。
原文摘要 · Abstract (English)
In conventional deep speaker embedding frameworks, the pooling layer aggregates all frame-level features over time and computes their mean and standard deviation statistics as inputs to subsequent segment-level layers. Such statistics pooling strategy produces fixed-length representations from variable-length speech segments. However, this method treats different frame-level features equally and discards covariance information. In this paper, we propose the Semi-orthogonal parameter pooling of Covariance matrix (SoCov) method. The SoCov pooling computes the covariance matrix from the self-attentive frame-level features and compresses it into a vector using the semi-orthogonal parametric vectorization, which is then concatenated with the weighted standard deviation vector to form inputs to the segment-level layers. Deep embedding based on SoCov is called ``sc-vector''. The proposed sc-vector is compared to several different baselines on the SRE21 development and evaluation sets. The sc-vector system significantly outperforms the conventional x-vector system, with a relative reduction in EER of 15.5% on SRE21Eval. When using self-attentive deep feature, SoCov helps to reduce EER on SRE21Eval by about 30.9% relatively to the conventional ``mean + standard deviation'' statistics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。