arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.11245cs.CLcs.LGcs.SDeess.AS
收藏

用于情感分析的端到端语音识别模型

Incorporating End-to-End Speech Recognition Models for Sentiment Analysis

University of Hamburg(汉堡大学);Knowledge Technology, Department of Informatics, University of Hamburg(汉堡大学信息学系知识技术)

Egor Lakomkin, Mohammad Ali Zamani, Cornelius Weber, Sven Magg, Stefan Wermter

摘要:

先前的工作表明,情感识别的协同效应相结合的几种方式,如听觉,视觉和转录的文本来估计说话人的情感状态。其中,语言情态对情感表达的评价起着至关重要的作用。然而,人工转录的口语文本实际上不能作为系统的输入。我们认为,在训练和评估阶段使用地面实况transmittance导致性能与现实世界的条件相比,显着的差异,因为口语文本必须在飞行中识别,并可能包含语音识别错误。在本文中,我们提出了一种方法集成的自动语音识别(ASR)输出与字符级递归神经网络的情感识别。此外,我们进行了几个实验,调查情感识别的人与机器人的互动,在一个噪声逼真的情况下,这是具有挑战性的ASR系统。我们量化的改进相比,只使用声学模态的情感识别。我们证明了这种方法在多模态情感强度语料库(MOSI)上的有效性,在二进制情感分类任务中实现了73,6%的准确率,超过了以前报道的仅使用声学输入的结果。此外,我们在MOSI数据集上设置了新的最先进性能(80.4%的准确率,2%的绝对改进)。

英文摘要:

Previous work on emotion recognition demonstrated a synergistic effect of combining several modalities such as auditory, visual, and transcribed text to estimate the affective state of a speaker. Among these, the linguistic modality is crucial for the evaluation of an expressed emotion. However, manually transcribed spoken text cannot be given as input to a system practically. We argue that using ground-truth transcriptions during training and evaluation phases leads to a significant discrepancy in performance compared to real-world conditions, as the spoken text has to be recognized on the fly and can contain speech recognition mistakes. In this paper, we propose a method of integrating an automatic speech recognition (ASR) output with a character-level recurrent neural network for sentiment recognition. In addition, we conduct several experiments investigating sentiment recognition for human-robot interaction in a noise-realistic scenario which is challenging for the ASR systems. We quantify the improvement compared to using only the acoustic modality in sentiment recognition. We demonstrate the effectiveness of this approach on the Multimodal Corpus of Sentiment Intensity (MOSI) by achieving 73,6% accuracy in a binary sentiment classification task, exceeding previously reported results that use only acoustic input. In addition, we set a new state-of-the-art performance on the MOSI dataset (80.4% accuracy, 2% absolute improvement).

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。

↑