探索多语言未见说话人情感识别：在多任务学习中利用共同注意力线索
Exploring Multilingual Unseen Speaker Emotion Recognition: Leveraging Co-Attention Cues in Multitask Learning
AI总结：
针对多语言语音情感识别难以泛化至未见说话人的问题，提出融合共同注意力与多任务学习的CAMuLeNet架构，基准测试显示其在未见说话人任务上平均提升约8%，还发布了印地语SER数据集BhavVani。
摘要：
现代深度学习技术的出现推动了语音情感识别（Speech Emotion Recognition, SER）领域的发展。然而，该领域现有大多数系统无法泛化到训练期间未见过的说话人。本研究聚焦于应对多语言SER的挑战，尤其是针对未见说话人的场景。我们提出了CAMuLeNet，这是一种利用基于共同注意力的融合与多任务学习来解决该问题的新型架构。此外，我们在5个现有多语言基准数据集（IEMOCAP、RAVDESS、CREMA-D、EmoDB和CaFE）上采用10折留说话人交叉验证，对Whisper、HuBERT、Wav2Vec2.0和WavLM的预训练编码器进行基准测试，并发布了一个针对印地语的新型SER数据集BhavVani。通过我们的交叉验证策略测定，CAMuLeNet在所有基准测试的未见说话人任务上平均提升约8%。
英文摘要：
Advent of modern deep learning techniques has given rise to advancements in the field of Speech Emotion Recognition (SER). However, most systems prevalent in the field fail to generalize to speakers not seen during training. This study focuses on handling challenges of multilingual SER, specifically on unseen speakers. We introduce CAMuLeNet, a novel architecture leveraging co-attention based fusion and multitask learning to address this problem. Additionally, we benchmark pretrained encoders of Whisper, HuBERT, Wav2Vec2.0, and WavLM using 10-fold leave-speaker-out cross-validation on five existing multilingual benchmark datasets: IEMOCAP, RAVDESS, CREMA-D, EmoDB and CaFE and, release a novel dataset for SER on the Hindi language (BhavVani). CAMuLeNet shows an average improvement of approximately 8% over all benchmarks on unseen speakers determined by our cross-validation strategy.
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。
