arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.08663eess.AS
收藏

基于伪多标签的无监督跨语言语音情感识别

Unsupervised Cross-Lingual Speech Emotion Recognition Using Pseudo Multilabel

Jin Li, Nan Yan, Lan Wang

摘要:

在过去的十年中,单一语言的语音情感识别(SER)通过深度学习方法取得了显着的成果。然而,跨语言SER仍然是一个挑战,在现实世界中的应用,由于源和目标域之间的分布有很大的差异。为了解决这个问题,我们提出了一个无监督的跨语言神经网络与伪多标签(NNPM),该网络经过训练,以学习外部存储器内的源域特征之间的情感相似性,以识别跨语言数据库中的情感。NNPM引入了一种新的方法,利用外部存储器来存储源域特征,并通过计算外部存储器和目标域特征之间的相似性来为每个目标域数据生成伪多标签。我们评估我们的方法对多种不同语言的语音情感数据库。实验结果表明,我们提出的方法显着提高了加权准确率(WA)在乌尔都语,Skropus,ShEMO和EMO-DB语料库的多个低资源的语言。为了便于进一步研究,代码可在https://github.com/happyjin/NNPM上获得

英文摘要:

Speech Emotion Recognition (SER) in a single language has achieved remarkable results through deep learning approaches in the last decade. However, cross-lingual SER remains a challenge in real-world applications due to a great difference between the source and target domain distributions. To address this issue, we propose an unsupervised cross-lingual Neural Network with Pseudo Multilabel (NNPM) that is trained to learn the emotion similarities between source domain features inside an external memory adjusted to identify emotion in cross-lingual databases. NNPM introduces a novel approach that leverages external memory to store source domain features and generates pseudo multilabel for each target domain data by computing the similarities between the external memory and the target domain features. We evaluate our approach on multiple different languages of speech emotion databases. Experimental results show our proposed approach significantly improves the weighted accuracy (WA) across multiple low-resource languages on Urdu, Skropus, ShEMO, and EMO-DB corpus. To facilitate further research, code is available at https://github.com/happyjin/NNPM

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。

↑