1. 基本信息
Ÿ王胜蓓，女，1986 年生
Ÿ 单位：天津工业大学计算机科学与技术学院
Ÿ 电话: **981
Ÿ QQ： **6
Ÿ 电子邮件： **6@qq.com
2. 研究方向
Ÿ信息隐藏、数字水印
Ÿ 篡改检测、多媒体安全认证
Ÿ 深度学习
3. 教育背景
Ÿ学位：博士| 2012.10 --- 2015.09
Ÿ 毕业院校：日本北陆先端科学技术大学院大学 信息科学
Japan advancedinstitute of science and technology (JAIST)
4. 科研与学术工作经历
2019/12–至今，天津工业大学， 计算机科学与技术学院，副教授 （硕士生导师）
2016/4–2019/11，天津工业大学， 计算机科学与技术学院， 讲师 （硕士生导师）
5. 主持或参加科研项目（课题）及人才计划项目情况
1.
语音声学参数篡改检测的关键理论及算法研究（**）
2. 天津市自然科学基金，6 万，2017/04-2020/03
基于线性预测频谱调制的语音水印及语音篡改检测技术研究（17JCQNJC00100）
3. 天津市教育委员会基金 ，6 万，2017/11-2020/10
即时通讯软件中语音安全及真伪鉴定技术研究（2017KJ089）
1.
针对语音信号的篡改检测理论及算法研究（19JCYBJC15600），第二参与人
2. 天津市教育委员会基金，6 万， 2018/11-2021/10
基于多目标对抗网络的语音安全及认证技术研究（2018KJ218），第二参与人
3. 天津市自然科学基金， 10 万，2016/10-2019/09
基于深度神经网络的市民大数据分析关键技术研究（16JCYBJC42300），第二参与人
4. 国家自然科学基金青年项目，20 万，2019/01-2021/12
基于门控卷积神经网络和长期记忆建模的文本分类模型（**），第三参与人
1.
6. 代表性研究成果
1.ShengbeiWang, Weitao Yuan, Masashi Unoki, Multi-subspace Echo Hidingbased on Time-Frequency Similarities of Audio Signals, IEEE/ACMTransactions on Audio, Speech, and Language Processing, vol. 28, pp.2349-2363, 2020.
3.Weitao Yuan, ShengbeiWang*, XiangruiLi, Masashi Unoki, Wenwu Wang, A Skip Attention Mechanism forMonaural Singing Voice Separation,IEEE Signal Processing Letters, vol. 26, no. 10, pp.1481-1485, 2019. (CCF-C 类期刊
4.ShengbeiWang, Weitao Yuan*, Jianming Wang, MasashiUnoki, Detection of Speech Tampering UsingSparse Representations and Spectral Manipulations Based Information Hiding,Speech Communication, 112, pp. 1–14,2019. (CCF-B
5.ShengbeiWang, Weitao Yuan, Jianming Wang, MasashiUnoki, “Inaudible speech watermarking based on self-compensated echo-hiding andsparse subspace clustering,” Proc. 44th International Conference on Acoustics,Speech and Signal Processing (ICASSP2019), pp. 2632 - 2636, 2019. (CCF-B 类会议)
7.Weitao Yuan, Boxin He, Shengbei Wang*,Jianming Wang, Unoki, Masashi
Unoki, Enhanced feature network for monaural singing voiceseparation, Speech Communication, vol.106, pp. 1-6, 2019. (CCF-B 类期刊)
8.ShengbeiWang,Weitao Yuan*, JianmingWang,Masashi Unoki, “Speech Watermarking based on robust principlecomponent analysis and formant manipulations,” Proc. 43rd InternationalConference on Acoustics, Speech and Signal Processing (ICASSP2018), pp. 2082-2086, 2018.(CCF-B 类会议)
9.Jianwu Dang, Shengbei Wang*, and Masashi Unoki, “Investigation into Vowel and Consonant Structures inArticulatory and Auditory Spaces using Laplacian eigenmaps,” Proc.41st International Conference on Acoustics, Speechand Signal Processing (ICASSP2016), pp. 5355-5359,2016. (CCF-B
10. BoxinHe, Shengbei Wang*, Weitao Yuan,Jianming Wang, Masashi Unoki,Data augmentation for monaural singing voice separation based on variationalautoencoder and generative adversarial network, IEEE International Conference on Multimedia and Expo (ICME)，pp.1354-1359, 2019,
11.
12.
13.ShengbeiWang* and MasashiUnoki, “Speech Watermarking Method based on Formant Tuning,” IEICE Trans. INF. & SYST., Enriched Multimedia, vol. E98-D, no. 1, pp. 29-37, Jan., 2015.
14.ShengbeiWang*, RyotaMiyauchi, Masashi Unoki, and Nam Soo Kim, “Tampering Detection Scheme forSpeech Signals using Formant Enhancement based Watermarking,” Journal ofInformation Hiding and Multimedia Signal Processing (JIHMSP), vol. 6, no. 6,pp. 1264-1283, Nov., 2015.
15.ShengbeiWang* and MasashiUnoki, “Watermarking of Speech Signals based on Formant Enhancement,” Proc.22nd European Signal Processing Conference (EUSIPCO2014), pp. 1257-1261,Portugal, 2014.
16.Shengbei Wang*, Xuyang Liu, XinDang, Jianming Wang, A robust speech
watermarking based onQuantization Index Modulation and Double Discrete Cosine Transform, 2017 10thInternational Congress on Image and Signal Processing, BioMedical Engineeringand Informatics (CISP-BMEI2017), pp. 1-6, 2017.
17.ShengbeiWang* and MasashiUnoki, “Hybrid Speech Watermarking based on Formant Enhancement and Cochlear Delay,” Proc. 10th Intelligent InformationHiding and Multimedia Signal Processing (IIHMSP2014), pp. 272-275, Japan, 2014.
18.ShengbeiWang* and MasashiUnoki, “Watermarking Method for Speech Signals based on Modifications to LSFs,”Proc. 9th Intelligent Information Hiding and Multimedia Signal Processing(IIHMSP2013), pp. 283-286, China, 2013.
19.Erick Christian Garcia Alvarze,
20.Masashi Unoki, Jessada Karnjana,
21.Nhut Minh Ngo, Shengbei Wang, Masashi Unoki, “Method of Digital-audioWatermarking Based on Cochlear Delay in Sub-bands,” Proc. 27th International Technical Conference on Circuits/Systems,Computers and Communications (ITC-CSCC 2012), D-W1-03, Japan, 2012.
