arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.11764cs.CLcs.AI
收藏

从高资源语言到低资源语言的迁移学习提高语音情感识别分类精度

Transfer learning from High-Resource to Low-Resource Language Improves Speech Affect Recognition Classification Accuracy

Fast Nuces

Sara Durrani, Umair Arshad

摘要:

语音情感识别是从音频数据中提取情感的问题。低资源语言语料库的落后和跨语料库的情感识别是一个困难的任务。我们提出了一种方法,在这种方法中,模型在高资源语言上进行训练,并进行微调以识别低资源语言中的影响。我们训练模型在相同的语料库设置上SAVEE,EMOVO,乌尔都语,IEMOCAP分别达到基线准确率60.45%,68.05%,80.34%,和56.58%。为了捕捉语言中情感的多样性,本文详细讨论了跨语料库评价。我们发现,通过将域目标数据添加到训练数据中,精度得到提高。最后,我们表明,低资源语言语音影响识别的性能得到改善,实现乌尔都语和意大利语语音影响的UAR为69.32和68.2。

英文摘要:

Speech Affect Recognition is a problem of extracting emotional affects from audio data. Low resource languages corpora are rear and affect recognition is a difficult task in cross-corpus settings. We present an approach in which the model is trained on high resource language and fine-tune to recognize affects in low resource language. We train the model in same corpus setting on SAVEE, EMOVO, Urdu, and IEMOCAP by achieving baseline accuracy of 60.45, 68.05, 80.34, and 56.58 percent respectively. For capturing the diversity of affects in languages cross-corpus evaluations are discussed in detail. We find that accuracy improves by adding the domain target data into the training data. Finally, we show that performance is improved for low resource language speech affect recognition by achieving the UAR OF 69.32 and 68.2 for Urdu and Italian speech affects.

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。

↑