基于任务自适应预训练的主动学习语音情感识别
Active Learning with Task Adaptation Pre-training for Speech Emotion Recognition
AI总结：
针对语音情感识别中预训练与下游任务信息差距大、微调耗时的问题，提出结合任务自适应预训练和主动学习的After框架，仅用20%样本即提升准确率8.45%并减少79%时间消耗。
摘要：
语音情感识别（SER）因其在人机交互、虚拟助手和心理健康辅助等多个领域的广泛应用而受到越来越多的关注。然而，现有的SER方法往往忽视了预训练语音识别任务与下游SER任务之间的信息差距，导致性能欠佳。此外，当前方法需要在每个特定语音数据集（如IEMOCAP）上进行大量时间的微调，这限制了它们在大规模噪声数据的现实场景中的有效性。为了解决这些问题，我们提出了一种基于主动学习（AL）的SER微调框架，称为After，该框架利用任务自适应预训练（TAPT）和AL方法来提升性能和效率。具体而言，我们首先使用TAPT来最小化预训练语音识别任务与下游语音情感识别任务之间的信息差距。然后，采用AL方法迭代地选择最具信息量和多样性的样本子集进行微调，从而减少时间消耗。实验表明，我们提出的方法After仅使用20%的样本，就将准确率提高了8.45%，并将时间消耗减少了79%。After的进一步扩展和消融研究进一步证实了其有效性以及对各种现实场景的适用性。我们的源代码已在Github上公开，以保证可复现性。（https://github.com/Clearloveyuan/AFTER）
英文摘要：
Speech emotion recognition (SER) has garnered increasing attention due to its wide range of applications in various fields, including human-machine interaction, virtual assistants, and mental health assistance. However, existing SER methods often overlook the information gap between the pre-training speech recognition task and the downstream SER task, resulting in sub-optimal performance. Moreover, current methods require much time for fine-tuning on each specific speech dataset, such as IEMOCAP, which limits their effectiveness in real-world scenarios with large-scale noisy data. To address these issues, we propose an active learning (AL)-based fine-tuning framework for SER, called \textsc{After}, that leverages task adaptation pre-training (TAPT) and AL methods to enhance performance and efficiency. Specifically, we first use TAPT to minimize the information gap between the pre-training speech recognition task and the downstream speech emotion recognition task. Then, AL methods are employed to iteratively select a subset of the most informative and diverse samples for fine-tuning, thereby reducing time consumption. Experiments demonstrate that our proposed method \textsc{After}, using only 20\% of samples, improves accuracy by 8.45\% and reduces time consumption by 79\%. The additional extension of \textsc{After} and ablation studies further confirm its effectiveness and applicability to various real-world scenarios. Our source code is available on Github for reproducibility. (https://github.com/Clearloveyuan/AFTER).
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。
