arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2312.03324eess.AS
收藏

使用具有特征划分与融合的变换模块的轻量级说话人验证

Lightweight Speaker Verification Using Transformation Module with Feature Partition and Fusion

Yanxiong Li, Zhongjie Jiang, Qisheng Huang, Wenchang Cao, Jialong Li

AI总结:

针对低资源终端说话人验证部署难题,提出即插即用的特征划分与融合变换模块,可在 AMCRN、ResNet34 和 ECAPA-TDNN 中显著降低复杂度并保持较低等错误率。

摘要:

尽管在降低说话人验证模型复杂度方面已经付出了许多努力,但在低资源终端上部署能够取得令人满意结果的说话人验证系统仍然具有挑战性。我们设计了一个执行特征划分和融合的变换模块,以实现轻量级说话人验证。该变换模块由多个简单但有效的操作组成,例如卷积、池化、均值、拼接、归一化和逐元素求和。它以即插即用的方式工作,可以方便地植入多种模型中,从而在保持模型误差的同时降低模型复杂度。首先,将输入特征划分为若干低维特征子集,以降低模型复杂度。然后,通过将每个特征子集与特征子集之间的相关信息相融合来更新该子集,以增强其表示能力。最后,将更新后的特征子集独立送入模型的块(一层或多层)进行进一步处理。从模型当前块输出的特征在被送入模型下一个块之前,会按照上述步骤进行处理。实验数据选自两个公开语音语料库(即 VoxCeleb1 和 VoxCeleb2)。结果表明,将该变换模块植入用于说话人验证的三个模型(即 AMCRN、ResNet34 和 ECAPA-TDNN)中,会略微增加模型误差,并显著降低模型复杂度。我们提出的方法在内存需求和计算复杂度方面总体上优于基线方法,同时具有更低的等错误率。它还能在不同长度的截断片段上良好泛化。

英文摘要:

Although many efforts have been made on decreasing the model complexity for speaker verification, it is still challenging to deploy speaker verification systems with satisfactory result on low-resource terminals. We design a transformation module that performs feature partition and fusion to implement lightweight speaker verification. The transformation module consists of multiple simple but effective operations, such as convolution, pooling, mean, concatenation, normalization, and element-wise summation. It works in a plug-and-play way, and can be easily implanted into a wide variety of models to reduce the model complexity while maintaining the model error. First, the input feature is split into several low-dimensional feature subsets for decreasing the model complexity. Then, each feature subset is updated by fusing it with the inter-feature-subsets correlational information to enhance its representational capability. Finally, the updated feature subsets are independently fed into the block (one or several layers) of the model for further processing. The features that are output from current block of the model are processed according to the steps above before they are fed into the next block of the model. Experimental data are selected from two public speech corpora (namely VoxCeleb1 and VoxCeleb2). Results show that implanting the transformation module into three models (namely AMCRN, ResNet34, and ECAPA-TDNN) for speaker verification slightly increases the model error and significantly decreases the model complexity. Our proposed method outperforms baseline methods on the whole in memory requirement and computational complexity with lower equal error rate. It also generalizes well across truncated segments with various lengths.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑