基于深度域适应CNN决策树的跨语料库情感识别

TN912.3; 在跨语料库语音情感识别中,由于目标域和源域样本不匹配,导致情感识别性能很差.为了提高跨语料库语音情感识别性能,本文提出一种基于深度域适应和卷积神经网络(Convolutional neural network,CNN)决策树模型的跨语料库语音情感识别方法.首先构建基于联合约束深度域适应的局部特征迁移学习网络,通过最小化目标域和源域在特征空间和希尔伯特空间的联合差异,挖掘两个语料库之间的相关性,学习从目标域到源域的可迁移不变特征.然后,为了降低跨语料库背景下多种情感间的易混淆情感的分类误差,依据情感混淆度构建CNN决策树多级分类模型,对多种情感先粗分类再细分类.使用CASIA,...

Full description

Saved in:
Bibliographic Details
Published in数据采集与处理 Vol. 38; no. 3; pp. 704 - 716
Main Authors 孙林慧, 赵敏, 王舜
Format Journal Article
LanguageChinese
Published 南京邮电大学通信与信息工程学院,南京210003 01.05.2023
Subjects
跨语料库语音情感识别
迁移学习
卷积神经网络
深度域适应
决策树模型
Online AccessGet full text

Cover

Abstract TN912.3; 在跨语料库语音情感识别中,由于目标域和源域样本不匹配,导致情感识别性能很差.为了提高跨语料库语音情感识别性能,本文提出一种基于深度域适应和卷积神经网络(Convolutional neural network,CNN)决策树模型的跨语料库语音情感识别方法.首先构建基于联合约束深度域适应的局部特征迁移学习网络,通过最小化目标域和源域在特征空间和希尔伯特空间的联合差异,挖掘两个语料库之间的相关性,学习从目标域到源域的可迁移不变特征.然后,为了降低跨语料库背景下多种情感间的易混淆情感的分类误差,依据情感混淆度构建CNN决策树多级分类模型,对多种情感先粗分类再细分类.使用CASIA,EMO-DB和RAVDESS三个语料库进行验证.实验结果表明,本文的跨语料库语音情感识别方法比CNN基线方法平均识别率高19.32％～31.08％,系统性能得到很大提升.
AbstractList TN912.3; 在跨语料库语音情感识别中,由于目标域和源域样本不匹配,导致情感识别性能很差.为了提高跨语料库语音情感识别性能,本文提出一种基于深度域适应和卷积神经网络(Convolutional neural network,CNN)决策树模型的跨语料库语音情感识别方法.首先构建基于联合约束深度域适应的局部特征迁移学习网络,通过最小化目标域和源域在特征空间和希尔伯特空间的联合差异,挖掘两个语料库之间的相关性,学习从目标域到源域的可迁移不变特征.然后,为了降低跨语料库背景下多种情感间的易混淆情感的分类误差,依据情感混淆度构建CNN决策树多级分类模型,对多种情感先粗分类再细分类.使用CASIA,EMO-DB和RAVDESS三个语料库进行验证.实验结果表明,本文的跨语料库语音情感识别方法比CNN基线方法平均识别率高19.32％～31.08％,系统性能得到很大提升.
Author 孙林慧
赵敏
王舜
AuthorAffiliation 南京邮电大学通信与信息工程学院,南京210003
AuthorAffiliation_xml – name: 南京邮电大学通信与信息工程学院,南京210003
Author_FL ZHAO Min
SUN Linhui
WANG Shun
Author_FL_xml – sequence: 1
  fullname: SUN Linhui
– sequence: 2
  fullname: ZHAO Min
– sequence: 3
  fullname: WANG Shun
Author_xml – sequence: 1
  fullname: 孙林慧
– sequence: 2
  fullname: 赵敏
– sequence: 3
  fullname: 王舜
BookMark eNo9j89Kw0AYxPdQwVr7Dh69JH673-4mAS8S_AelXvRcNtusGEoKBhFvorV4EopS0Es8iSCliIdCnsdN61sYUYSBgRmY4bdCamk_jQlZo-BSiehtJC4F4E4A6LkMGLpQifo1Uv_Pl0kzy06iqpRc0kDWyabNi8_irpy92-LF5vnX5ZUtHsJ22w4_5pNx-TyaPw0Ws9fFdFKOH21xX17flIN8MR3a27dVsmRUL4ubf94gRzvbh-Ge0zrY3Q-3Wk5GAX1HConCZzpQHDAyyvcl51qDVEKDplHsC-VpxkF7gtJuoCITG1SsK7RizCA2yPrv7rlKjUqPO0n_7DStHjtZopML3fvBBaxg8Rt8ymEB
ClassificationCodes TN912.3
ContentType Journal Article
Copyright Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
Copyright_xml – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved.
DBID 2B.
4A8
92I
93N
PSX
TCJ
DOI 10.16337/j.1004-9037.2023.03.018
DatabaseName Wanfang Data Journals - Hong Kong
WANFANG Data Centre
Wanfang Data Journals
万方数据期刊 - 香港版
China Online Journals (COJ)
China Online Journals (COJ)
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
DocumentTitle_FL Cross?Corpus Emotion Recognition Based on Deep Domain Adaptation and CNN Decision Tree
EndPage 716
ExternalDocumentID sjcjycl202303018
GrantInformation_xml – fundername: (国家自然科学基金); (教育部国家留学基金)
  funderid: (国家自然科学基金); (教育部国家留学基金)
GroupedDBID 2B.
4A8
92I
93N
ADMLS
ALMA_UNASSIGNED_HOLDINGS
PSX
TCJ
ID FETCH-LOGICAL-s1038-6563582c9a403bfa88644cc06a5c0c1be85a7c240c7511d9abfef3a2d5ca22f33
ISSN 1004-9037
IngestDate Thu May 29 04:00:12 EDT 2025
IsPeerReviewed false
IsScholarly true
Issue 3
Keywords 跨语料库语音情感识别
迁移学习
卷积神经网络
深度域适应
决策树模型
Language Chinese
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-s1038-6563582c9a403bfa88644cc06a5c0c1be85a7c240c7511d9abfef3a2d5ca22f33
PageCount 13
ParticipantIDs wanfang_journals_sjcjycl202303018
PublicationCentury 2000
PublicationDate 2023-05-01
PublicationDateYYYYMMDD 2023-05-01
PublicationDate_xml – month: 05
  year: 2023
  text: 2023-05-01
  day: 01
PublicationDecade 2020
PublicationTitle 数据采集与处理
PublicationTitle_FL Journal of Data Acquisition & Processing
PublicationYear 2023
Publisher 南京邮电大学通信与信息工程学院,南京210003
Publisher_xml – name: 南京邮电大学通信与信息工程学院,南京210003
SSID ssib023646196
ssib001102757
ssib000459638
ssib001164671
ssib006568634
ssib002264227
ssib036439733
ssib057620134
ssib023167944
ssib051372606
Score 2.3451252
Snippet TN912.3; 在跨语料库语音情感识别中,由于目标域和源域样本不匹配,导致情感识别性能很差.为了提高跨语料库语音情感识别性能,本文提出一种基于深度域适应和卷积神经网络(Convolutional neural...
SourceID wanfang
SourceType Aggregation Database
StartPage 704
Title 基于深度域适应CNN决策树的跨语料库情感识别
URI https://d.wanfangdata.com.cn/periodical/sjcjycl202303018
Volume 38
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1Na9RANLT14kUUFb-p4By3JjOZzAx4ye5mKYI9tdBbyadSZAV3e7An0Vo8CaIU9LKeRJBSxENhf4_Z1n_hey9pdmoVqhDC8ObNm_eRybyXzJtxnDu5m2VSqrilc5NBgOLzVpJBzJMGSSClkKIoMN_5wVKwuOLfX5WrM7P2qqWNYbKQbv4xr-R_rAowsCtmyf6DZRuiAIAy2BfuYGG4n8rGLJLM9Fg7ZJGPdx2xKGBtxdoeVgEkDGocuCKDyxo0r6uM31lawrKGJoJFioVdZgKkELrMeAgxQNNnkUaaocZC2EM0wAFMY45ICYRowbSkgk_dEbImBjSU27YfTBSgrUv4XRZGxJ7CCwqmTQ1BKE1CSRb6xAmwBCI0XxOppkuMAL2IGUX0AKimKMC9xKvqUvemNQqJ6zaiAIemY38C4daCQ3poSY4udUHKDjvEMifegS-f-iBOQ1UzhuonrZvKRKA8zxKrgQDPHmoL1QmalmQNTaxZdEDMkMOYOMkJx_8nwppgcOGPcauNbo5mIKGtkSas6URVRzPXnomqslJPTHqBoH0T1hca4guoJdq8t57cjm8pPlhP15-ljxEJI2I965zhEGVx64tE7e0fez2Dp8iV9ZPcw73prGgCc7I5t9OWAx1Mdx_kuOmClYaNRxdA-N54w4Kc42n0IT2hINpu6iEyBm-1WidyJGi9Ng81cPcv8lM2Xr-I-w8tx3H5vHOujvjmw2r4XnBmNh9ddO6Vo_GP8ZvJ_rdy_LkcjX4-f1GO38OALLe_H-zuTD69Pfi4dbj_5XBvd7LzoRy_m7x8NdkaHe5tl6-_XnJWetFyZ7FVH2TSGuD5Ay1QBCakpyb2XZEUsdYQhaSpG8QydVMvybWMVQq-daog_slMnBR5IWKeyTTmvBDisjPXf9LPrzjzsYbWPDFFUUDsk4jEGK0LV-VB4mW64Fed27W0a_WLarD2u7mvnQLnunN2OtJuOHPDpxv5TXC_h8ktekh-AeAlnV8
linkProvider Directory of Open Access Journals
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E5%9F%BA%E4%BA%8E%E6%B7%B1%E5%BA%A6%E5%9F%9F%E9%80%82%E5%BA%94CNN%E5%86%B3%E7%AD%96%E6%A0%91%E7%9A%84%E8%B7%A8%E8%AF%AD%E6%96%99%E5%BA%93%E6%83%85%E6%84%9F%E8%AF%86%E5%88%AB&rft.jtitle=%E6%95%B0%E6%8D%AE%E9%87%87%E9%9B%86%E4%B8%8E%E5%A4%84%E7%90%86&rft.au=%E5%AD%99%E6%9E%97%E6%85%A7&rft.au=%E8%B5%B5%E6%95%8F&rft.au=%E7%8E%8B%E8%88%9C&rft.date=2023-05-01&rft.pub=%E5%8D%97%E4%BA%AC%E9%82%AE%E7%94%B5%E5%A4%A7%E5%AD%A6%E9%80%9A%E4%BF%A1%E4%B8%8E%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E5%8D%97%E4%BA%AC210003&rft.issn=1004-9037&rft.volume=38&rft.issue=3&rft.spage=704&rft.epage=716&rft_id=info:doi/10.16337%2Fj.1004-9037.2023.03.018&rft.externalDocID=sjcjycl202303018
thumbnail_s http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fsjcjycl%2Fsjcjycl.jpg