arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.06112cs.CLcs.SDeess.AS
收藏

超越孤立的话语:会话情感识别

Beyond Isolated Utterances: Conversational Emotion Recognition

Johns Hopkins University(约翰斯·霍普金斯大学)

Raghavendra Pappagari, Piotr Żelasko, Jesús Villalba, Laureano Moro-Velazquez, Najim Dehak

摘要:

语音情感识别是指根据说话人的语音记录来识别说话人的情感状态。虽然目前大多数的方法都集中在从孤立的话语推断情感,我们认为,这是不足以实现会话情感识别(CER),它涉及到在对话中识别情感。在这项工作中,我们提出了几种方法CER治疗它作为一个序列标记任务。我们研究了CER的Transformer架构,并使用IEMOCAP语料库在上下文和无上下文场景下将其与ResNet-34和BiLSTM架构进行了比较。基于自我注意力机制的内部工作原理,我们提出了DiverseCatAugment(DCA),一种增强方案,它将Transformer模型的性能提高了3.3%的绝对微f1,对孤立的话语提高了3.6%。我们通过引入对话者感知的Transformer模型进一步提高了性能,在该模型中,我们学习对话者索引嵌入的字典来利用日记化的对话。

英文摘要:

Speech emotion recognition is the task of recognizing the speaker's emotional state given a recording of their utterance. While most of the current approaches focus on inferring emotion from isolated utterances, we argue that this is not sufficient to achieve conversational emotion recognition (CER) which deals with recognizing emotions in conversations. In this work, we propose several approaches for CER by treating it as a sequence labeling task. We investigated transformer architecture for CER and, compared it with ResNet-34 and BiLSTM architectures in both contextual and context-less scenarios using IEMOCAP corpus. Based on the inner workings of the self-attention mechanism, we proposed DiverseCatAugment (DCA), an augmentation scheme, which improved the transformer model performance by an absolute 3.3% micro-f1 on conversations and 3.6% on isolated utterances. We further enhanced the performance by introducing an interlocutor-aware transformer model where we learn a dictionary of interlocutor index embeddings to exploit diarized conversations.

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。

↑