面向领域特定跨语料库语音情感识别方法
Towards Domain-Specific Cross-Corpus Speech Emotion Recognition Approach
AI总结：
针对跨语料库SER中的特征分布失配问题，提出融合声学知识双稀疏约束的AKTLR迁移子空间方法，并在EmoDB、eNTERFACE和CASIA上验证其优于现有方法。
摘要：
跨语料库语音情感识别（SER）因特征分布不匹配而构成挑战，这可能降低既有SER方法的性能。本文中，我们通过提出一种名为声学知识引导迁移线性回归（AKTLR）的新型迁移子空间学习方法来应对这一挑战。现有方法往往忽视与SER相关的领域特定知识，并简单地将跨语料库SER视为通用迁移学习任务；与之不同，我们的AKTLR方法建立在精心设计的声学知识引导双稀疏约束机制之上。该机制强调极简声学参数特征集在缓解分类器过度适应方面的潜力，这是SER中经实验验证的声学知识，使其相比使用大型特征集能够在跨语料库SER任务中实现更优泛化。通过该机制，我们将简单的迁移线性回归模型扩展为AKTLR。这一扩展充分发挥其能力，从用于描述语音信号的既有声学参数特征集中，在两个尺度上寻求具有情感区分性且语料库不变的特征：有贡献的声学参数组，以及每个有贡献组内的组成元素。我们在三个广泛使用的语音情感语料库EmoDB、eNTERFACE和CASIA上，通过大量跨语料库SER实验评估了所提方法。结果证实了该方法的有效性和优越性能，其优于近期最先进的基于迁移子空间学习和深度迁移学习的跨语料库SER方法。此外，我们的工作提供了实验证据，支持将领域特定知识纳入迁移学习模型以解决跨语料库SER任务的可行性和优越性。
英文摘要：
Cross-corpus speech emotion recognition (SER) poses a challenge due to feature distribution mismatch, potentially degrading the performance of established SER methods. In this paper, we tackle this challenge by proposing a novel transfer subspace learning method called acoustic knowledgeguided transfer linear regression (AKTLR). Unlike existing approaches, which often overlook domain-specific knowledge related to SER and simply treat cross-corpus SER as a generic transfer learning task, our AKTLR method is built upon a well-designed acoustic knowledge-guided dual sparsity constraint mechanism. This mechanism emphasizes the potential of minimalistic acoustic parameter feature sets to alleviate classifier overadaptation, which is empirically validated acoustic knowledge in SER, enabling superior generalization in cross-corpus SER tasks compared to using large feature sets. Through this mechanism, we extend a simple transfer linear regression model to AKTLR. This extension harnesses its full capability to seek emotiondiscriminative and corpus-invariant features from established acoustic parameter feature sets used for describing speech signals across two scales: contributive acoustic parameter groups and constituent elements within each contributive group. Our proposed method is evaluated through extensive cross-corpus SER experiments on three widely-used speech emotion corpora: EmoDB, eNTERFACE, and CASIA. The results confirm the effectiveness and superior performance of our method, outperforming recent state-of-the-art transfer subspace learning and deep transfer learning-based cross-corpus SER methods. Furthermore, our work provides experimental evidence supporting the feasibility and superiority of incorporating domain-specific knowledge into the transfer learning model to address cross-corpus SER tasks.
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。
