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 2101.01356cs.SDcs.LGeess.AS
收藏

多语言语音情感识别中的固定MAML Few Shot分类

Fixed-MAML for Few Shot Classification in Multilingual Speech Emotion Recognition

Indian Institute of Information Technology, Guwahati(古瓦哈提印度信息技术研究所);Cardiff University(卡迪夫大学)

Anugunj Naman, Chetan Sinha, Liliana Mancini

摘要:

本文分析了将少样本学习应用于语音情感识别任务的可行性。目前的语音情感识别模型工作得非常好,但当输入是多语言时就失败了。此外,在训练这类模型时,只有在训练语料量很大时,模型的性能才合适。当选择一种不太流行或晦涩的语言时,大型训练语料库的可用性是一个重要的问题。我们试图通过将这个问题转化为一个少样本学习问题来解决多语言和缺乏可用数据的挑战。我们建议放宽假设,所有N类的N路K-shot问题是新的,并定义一个N+F的方式问题,其中N和F是情感类和预定义的固定类的数量,分别。我们提出了这种修改模型不可知元学习(MAML)算法来解决这个问题,并称之为F-MAML。这种修改比原始MAML的性能更好,并且优于ESPRIFilm数据集。

英文摘要:

In this paper, we analyze the feasibility of applying few-shot learning to speech emotion recognition task (SER). The current speech emotion recognition models work exceptionally well but fail when then input is multilingual. Moreover, when training such models, the models' performance is suitable only when the training corpus is vast. This availability of a big training corpus is a significant problem when choosing a language that is not much popular or obscure. We attempt to solve this challenge of multilingualism and lack of available data by turning this problem into a few-shot learning problem. We suggest relaxing the assumption that all N classes in an N-way K-shot problem be new and define an N+F way problem where N and F are the number of emotion classes and predefined fixed classes, respectively. We propose this modification to the Model-Agnostic MetaLearning (MAML) algorithm to solve the problem and call this new model F-MAML. This modification performs better than the original MAML and outperforms on EmoFilm dataset.

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。

↑