arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.01579eess.AScs.CLcs.SD
收藏

副语言表征是语音情感识别所需的全部吗?

Are Paralinguistic Representations all that is needed for Speech Emotion Recognition?

IIIT-Delhi(德里印度信息技术学院);University of Tartu(塔尔图大学)

Orchid Chetia Phukan, Gautam Siddharth Kashyap, Arun Balaji Buduru, Rajesh Sharma

AI总结:

针对副语言预训练模型表征缺乏多语言SER评估及基准测试的问题,该研究对比5种SOTA预训练模型表征,发现TRILLsson表征因能有效捕捉音高、语调等特征,在多语言语音情感识别中表现最优。

摘要:

预训练模型(PTM)表征的可用性推动了语音情感识别(SER)的长足进展。尤其是经副语言语音处理训练的PTM生成的表征,已在SER任务中展现出当前最优(SOTA)性能。但这类副语言PTM表征尚未在英语以外的语言环境中接受SER任务评估,也未在SUPERB、EMO-SUPERB、ML-SUPERB等基准中针对SER展开研究,导致难以衡量其在多语言场景下的SER效用。为填补这一空白,我们对5种SOTA PTM表征开展了全面对比研究。结果显示,副语言PTM(TRILLsson)表征表现最佳,其性能优势源于它能比其他PTM表征更有效地捕捉音高、语调及其他语音特征。

英文摘要:

Availability of representations from pre-trained models (PTMs) have facilitated substantial progress in speech emotion recognition (SER). Particularly, representations from PTM trained for paralinguistic speech processing have shown state-of-the-art (SOTA) performance for SER. However, such paralinguistic PTM representations haven't been evaluated for SER in linguistic environments other than English. Also, paralinguistic PTM representations haven't been investigated in benchmarks such as SUPERB, EMO-SUPERB, ML-SUPERB for SER. This makes it difficult to access the efficacy of paralinguistic PTM representations for SER in multiple languages. To fill this gap, we perform a comprehensive comparative study of five SOTA PTM representations. Our results shows that paralinguistic PTM (TRILLsson) representations performs the best and this performance can be attributed to its effectiveness in capturing pitch, tone and other speech characteristics more effectively than other PTM representations.

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。

↑