一种用于增强跨语言语音情感识别的层锚定策略
A Layer-Anchoring Strategy for Enhancing Cross-Lingual Speech Emotion Recognition
AI总结：
针对跨语言SER中仅使用预训练模型末层的问题，提出层锚定机制以利用多层信息促进情感迁移，并在MSP-Podcast和BIIC-Podcast上验证，BIIC-Podcast最佳UAR达60.21%。
摘要：
跨语言语音情感识别（SER）对于广泛的日常应用非常重要。尽管近期的SER研究在情感训练中严重依赖大型预训练模型，但现有研究往往只关注这些模型的最后一个transformer层。然而，鉴于这些模型的任务特定性质和分层架构，每个transformer层都封装了不同层级的信息。利用这种分层结构，本研究聚焦于嵌入在不同层中的信息。通过考察不同语言间的层特征相似性，我们提出了一种称为层锚定机制的新颖策略，以促进跨语言SER任务中的情感迁移。我们使用两个不同语言的情感语料库（MSP-Podcast和BIIC-Podcast）评估了该方法，在BIIC-Podcast语料库上取得了60.21%的最佳UAR性能。分析揭示了有关常用预训练模型行为的有趣洞见。
英文摘要：
Cross-lingual speech emotion recognition (SER) is important for a wide range of everyday applications. While recent SER research relies heavily on large pretrained models for emotion training, existing studies often concentrate solely on the final transformer layer of these models. However, given the task-specific nature and hierarchical architecture of these models, each transformer layer encapsulates different levels of information. Leveraging this hierarchical structure, our study focuses on the information embedded across different layers. Through an examination of layer feature similarity across different languages, we propose a novel strategy called a layer-anchoring mechanism to facilitate emotion transfer in cross-lingual SER tasks. Our approach is evaluated using two distinct language affective corpora (MSP-Podcast and BIIC-Podcast), achieving a best UAR performance of 60.21% on the BIIC-podcast corpus. The analysis uncovers interesting insights into the behavior of popular pretrained models.
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。
