朱敏,姜芃旭,赵力.全卷积循环神经网络的语音情感识别[J].声学技术,2021,40(5):645~651 |
全卷积循环神经网络的语音情感识别 |
Speech emotion recognition based on full convolution recurrent neural network |
投稿时间:2020-08-15 修订日期:2020-12-21 |
DOI:10.16300/j.cnki.1000-3630.2021.05.009 |
中文关键词: 神经网络 语音情感 特征提取 |
英文关键词: neural network speech emotion feature extraction |
基金项目:国家自然科学基金项目(61673108、61571106)、国家重点研发计划(2018YFB1305203)。 |
|
摘要点击次数: 625 |
全文下载次数: 419 |
中文摘要: |
语音情感识别是人机交互的热门研究领域之一。然而,由于缺乏对语音中时频相关信息的研究,导致情感信息挖掘深度不够。为了更好地挖掘语音中的时频相关信息,提出了一种全卷积循环神经网络模型,采用并行多输入的方式组合不同模型,同时从两个模块中提取不同功能的特征。利用全卷积神经网络(Fully Convolutional Network,FCN)学习语音谱图特征中的时频相关信息,同时,利用长短期记忆(Long Short-Term Memory,LSTM)神经网络来学习语音的帧级特征,以补充模型在FCN学习过程中缺失的时间相关信息,最后,将特征融合后使用分类器进行分类,在两个公开的情感数据集上的测试验证了所提算法的优越性。 |
英文摘要: |
Speech emotion recognition is one of the hot research fields of human-computer interaction. However, lack of researches on speech time-frequency information leads to the insufficient depth of exploring emotional information. To better explore the time-frequency related information in speech, a novel fully convolutional recurrent neural network model is proposed, in which, the multi-input parallel model combination method is used to extract features of different functions from two modules. The fully convolutional network (FCN) is used to learn the time-frequency related information in the features of speech spectrogram, and long short-term memory neural network (LTSM) is used to learn the frame-level features of speech to supplement the missing time-dependent information during FCN learning. Finally, the features are fused and classified by classifier. Experiments on two public emotional data sets show the superiority of the proposed algorithm. |
查看全文
查看/发表评论 下载PDF阅读器 |
关闭 |