本文研究 WavLM Large 在语音情感识别中的微调策略，在 MSP Podcast Corpus 上利用性别与语义信息开展实验，并形成提交 2024 挑战赛的最终模型。
摘要：
近来，将语音自监督模型（SSL）用于下游任务引起了广泛关注。尽管大型预训练模型通常优于从头训练的小型模型，但关于最佳微调策略的问题仍然普遍存在。本文中，我们探索了 WavLM Large 模型在 MSP Podcast Corpus 上用于语音情感识别任务的微调策略。更具体地说，我们开展了一系列实验，重点是利用话语中的性别和语义信息。随后，我们总结了研究发现，并描述了用于提交 Speech Emotion Recognition Challenge 2024 的最终模型。
英文摘要：
Recently, the usage of speech self-supervised models (SSL) for downstream tasks has been drawing a lot of attention. While large pre-trained models commonly outperform smaller models trained from scratch, questions regarding the optimal fine-tuning strategies remain prevalent. In this paper, we explore the fine-tuning strategies of the WavLM Large model for the speech emotion recognition task on the MSP Podcast Corpus. More specifically, we perform a series of experiments focusing on using gender and semantic information from utterances. We then sum up our findings and describe the final model we used for submission to Speech Emotion Recognition Challenge 2024.
Vesper: A Compact and Effective Pretrained Model for Speech Emotion Recognition
School of Electronic and Information Engineering, South China University of Technology（华南理工大学电子与信息学院）；School of Software Engineering, South China University of Technology（华南理工大学软件学院）；School of Future Technology, South China University of Technology（华南理工大学未来技术学院）；Pazhou Laboratory（琶洲实验室）
Crab: Multi Layer Contrastive Supervision to Improve Speech Emotion Recognition Under Both Acted and Natural Speech Condition
Dept. of Computer Engineering and Automation (DCA), Faculdade de Engenharia Elétrica e de Computação（计算机工程与自动化系（DCA）、电气与计算机工程学院）；AI Lab.（人工智能实验室）；Institute of Computing, Universidade Estadual de Campinas, UNICAMP（计算学院，坎皮纳斯州立大学，UNICAMP）
Soft Clustering Anchors for Self-Supervised Speech Representation Learning in Joint Embedding Prediction Architectures
Carnegie Mellon University（卡内基梅隆大学）；New York University（纽约大学）；James Silberrad Brown Center for AI（詹姆斯·西伯拉德·布朗人工智能中心）；Columbia University（哥伦比亚大学）；Northeastern University（东北大学）；Stanford University（斯坦福大学）；Amazon GenAI（亚马逊生成人工智能）
