...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International Journal of Engineering Trends and Technology >A Speech-based Sentiment Analysis using Combined Deep Learning and Language Model on Real-Time Product Review
【24h】

A Speech-based Sentiment Analysis using Combined Deep Learning and Language Model on Real-Time Product Review

机译：基于语音的情感分析，使用组合深度学习和语言模型在实时产品评论中

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Sentiment analysis is the area of study in Natural Language Processing (NLP), where it has gained its popularity in text analytics for making any kind of purchase decision. Also, there is a need for speechbased sentiment analysis in realworld applications for providing a better quality of service. But the work carried out in the speech domain has gained very less attention. So, this paper proposed a speech sentiment analysis model by considering spectrogram as an acoustic feature. The spectrogram features are trained over a deep learning model and an Ngram Language model. A combined Convolutional Neural Network (CNN) and BidirectionalRecurrent Neural Network (BiRNN) architecture frameworks are implemented for acoustic modeling and a bigram language model to calculate the likelihood of a particular word sequence from the spoken utterance. NLP techniques like the Vader Sentiment Intensity Analyzer function is used for performing the sentiment analysis. The experimental results are analyzed in terms of Word Error Rate (WER) and Character Error Rate (CER) and proved that the proposed model holds outperforming WER and CER of 5.7% and 3 % when compared with the traditional Automatic Speech Recognition (ASR) models. The obtained sentiment analysis results are measured using correctly classified instances, precision, recall, and f1score using various machine learning algorithms. The logistic Regression algorithm proved to achieve improved accuracy of 90% with the proposed speech sentiment analysis model.
机译：情绪分析是自然语言处理（NLP）的研究领域，在那里它在文本分析中获得了普及，以便制作任何购买决定。此外，RealWorld应用程序需要语音情绪分析，以提供更好的服务质量。但是讲话域中进行的工作已经非常不那么关注。因此，本文提出了一种通过考虑光谱图作为声学特征的语音情绪分析模型。频谱图特征在深度学习模型和NARM语言模型上培训。为声学建模和BIGRAM语言模型实现了组合的卷积神经网络（CNN）和BIRNN）架构框架以计算来自口头话语的特定单词序列的可能性。像VADER情绪强度分析仪一样的NLP技术用于进行情感分析。根据字错误率（WER）和字符错误率（CER），分析了实验结果，并证明了与传统的自动语音识别（ASR）模型相比，所提出的模型保持优于5.7％和3％的CER。 。使用各种机器学习算法使用正确的分类实例，精确度，召回和F1Score来测量所获得的情绪分析结果。逻辑回归算法证明，通过提出的语音情绪分析模型实现了90％的提高精度。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号