Publications

Journal papers

• Javier Tejedor; Doroteo T. Toledano; Dong Wang; Simon King; Jose Colas, "Feature analysis for discriminative confidence estimation in Spoken Term Detection", Computer Speech and Language,28 (2014), pp. 1083-1114.

• Y. Xia, W. Su, R. Y.K. Lau & Y. Liu. Discovering latent commercial networks from online financial news articles. Enterprise Information Systems. Volume 7, Issue 3, pp.303-331, 2013

• E. Cambria, B. Schuller, Y. Xia, C. Havasi, "New Avenues in Opinion Mining and Sentiment Analysis," IEEE Intelligent Systems, Vol. 28, No. 2, pp. 15-21, March-April 2013

• C. Zhang, Y. Liu, Y. Xia, X. Wang, C.-H. Lee, “Reliable Accent-Specific Unit Generation with Discriminative Dynamic Gaussian Mixture Selection for Multi-Accent Chinese Speech Recognition,” IEEE Transactions on Audio, Speech and Language Processing: Volume:21, Issue: 10, pp. 2073 – 2084. 2013

• Nakhat Fatima, Xiaojun Wu and Thomas Fang Zheng, “Speech Unit Category based Short Utterance Speaker Recognition,” Computer Science and Information Systems (ComSIS) Vol. 9, No. 4, pp. 1407-1430, Special Issue on Recent Advances in Systems and Informatics, December 2012

• Dong Wang, Ravichander Vipperla, Nick Evans, Thomas Fang Zheng, "Online Non-negative Convolutive Pattern Learning for Speech Signals", IEEE trans. on signal processing, vol.61, no.1, pp.44-56.

• Dong Wang, Simon King, Joe Frankel, Ravichander Vipperla, Nick Evans, Raphael Troncy, "Direct Posterior Confidence Estimation for Out-of-Vocabulary Spoken Term Detection", ACM Trans. on Information Systems, vol.30, no.3, August, 2012.

• Dong Wang, Javier Tejedor, Simon King, Joe Frankel "Term-dependent Confidence Normalization for Out-of-Vocabulary Spoken Term Detection", Journal of Computer Science and Technology(JCST), vol.27, no.2, 2012.

• Nick Evans, Simon Bozonnet, Dong Wang, Corinne Fredouille and Raphael Troncy, "A Comparative Study of Bottom-up and Top-down Approaches to Speaker Diarization ", IEEE Trans. on Audio, Speech and Language Processing,vol.20, no.2, 2012.

• Javier Tejedor, Alejandro Echeverria Dong Wang, Ravichander Vipperla, "Evolutionary discriminative confidence estimation for spoken term detection ", Multimedia tools and applications, no.4, 2011.

• Yunqing Xia, Weifeng Su, Raymond Y.K. Lau & Yi Liu. Discovering latent commercial networks from online financial news articles. Enterprise Information Systems. 2012. DOI:10.1080/17517575.2011.621093.

• Raymond Y. K. Lau, S. Y. Liao, Ron Chi-Wai Kwok, Kaiquan Xu, Yunqing Xia, Yuefeng Li: Text mining and probabilistic language modeling for online review spam detection. ACM Trans. Management Inf. Syst. 2(4): 25 (2011)

• Dong Wang, Simon King, "Letter-to-Sound Pronunciation Prediction using Conditional Random Field", IEEE Signal Processing Letters, vol 18, no.2, February 2011 , pp 122-125.

• Dong Wang, Simon King, Joe Frankel, "Stochastic Pronunciation Modelling for Out-of-Vocabulary Term Detection", IEEE transaction on Acoustic, Speech and Language Processing, vol.18, no.8, November 2010.

• Yunqing Xia, Linlin Wang and Kam-Fai Wong. Sentiment Vector Space Model for Lyric-based Song Sentiment Classification. International Journal of Computer Processing of Oriental Languages, Vol. 21, No. 4 (2008): 331-345.

• Kam-Fai Wong, Yunqing Xia, Ruifeng Xu, Mingli Wu; Wenjie Li. Pattern-Based Opinion Mining for Stock Market Trend Prediction. International Journal of Computer Processing of Oriental Languages, Vol. 21, No. 4 (2008): 347-361.

• Javier Tejedor, Dong Wang, Joe Frankel, Simon King, Jose Colas, A comparison of grapheme and phoneme-based units for spoken term detection in Spanish", Speech Communication, 60(11-12):980-991, 2008.

• 唐国瑜, 夏云庆, 张民, 郑方. 基于跨语言广义向量空间模型的跨语言文档聚类方法. 中文信息学报，2012年第2期，Vol.26, No.2: 116-120。

• 张剑峰，夏云庆，姚建民. 微博文本处理研究综述. 中文信息学报，2012年第4期，Vol.26, No.4: 22-27。

• 夏云庆，杨莹，张鹏洲，刘宇飞. 基于情感向量空间模型的歌词情感分析.中文信息学报， 2010年01期，99-103.

• 郝博一，夏云庆，邬晓钧，郑方，刘轶. 基于泛化和繁殖的自举式意见目标抽取方法. 清华大学学报(自然科学版), 49(S1):1333-1338, 2009年7月

Conference papers

2014

• ATVS-CSLT-HCTLab System for NIST 2013 Open Keyword Search Evaluation, IberSPEECH 2014. To appear at LNCS/LNAI Proceedings.

• Jun Wang, Dong Wang, Ziwei Zhu, Thomas Fang Zheng, Frank Soong, Discriminative Scoring for Speaker Recognition Based on I-vectors, APSIPA 2014, to appear.

• Chao Xing, Dong Wang, Xuwei Zhang, Chao Liu, document classification based on i-vector distributions, APSIPA 2014, to appear.

• Jun Wang, Lantian Li, Dong Wang, Thomas Fang Zheng, Research on generalization property of time-varying Fbank-weighted MFCC for i-vector based speaker verification, ISCSLP 2014 (in Chinese)

• Fanhu Bie, Dong Wang, Thomas Fang Zheng, Truncated speech for speaker recognition, ISCSLP 2014 (in Chinese)

• Rong Liu, Dong Wang, Chao Xing, Text classification based on word vectors, ISCSLP 2014 (in Chinese).

• Chao Liu, Dong Wang, Zhiyong Zhang, "Pruning Deep Neural Networks by Optimal Brain Damage", Interspeech 2014.

• Fanhu Bie, Jun Wang, Dong Wang, Thomas Fang Zheng, "BLOCK-WISE TRAINING FOR I-VECTOR", ChinaSIP 2014

• Xiangtao Meng, Chao Liu, Zhiyong Zhang, Dong Wang, "NOISY TRAINING FOR DEEP NEURAL NETWORKS", ChinaSIP2014

2013

• Fanhu Bie, Dong Wang, Thomas Fang Zheng, Javier Tejedor, Ruxin Chen, "Emotional Adaptive Training for Speaker Verification", APSIPA 2013.

• Jun Wang, Dong Wang, Xiaojun Wu, Thomas Fang Zheng and Javier Tejedor, "Sequential Model Adaptation for Speaker Verification", Interspeech 2013.

• Jun Qi, Dong Wang and Javier Tejedor, "Subspace Models for Bottleneck Features", Interspeech 2013.

• Jun Qi, Dong Wang, Ji Xu and Javier Tejedor, "Bottleneck Features based on Gammatone Frequency Cepstral Coefficients", Interspeech 2013.

• Jun Wang, Dong Wang, Xiaojun Wu, Thomas Fang Zheng, "SEQUENTIAL UBM ADAPTATION FOR SPEAKER VERIFICATION", ChinaSip 2013.

• Fanhu Bie, Dong Wang, Thomas Fang Zheng, "EMOTIONAL SPEAKER VERIFICATION WITH LINEAR ADAPTATION", ChinaSip 2013.

• Jun Qi, Dong Wang, Yi Jiang, Runsheng Liu "AUDITORY FEATURES BASED ON GAMMATONE FILTERS FOR ROBUST SPEECH RECOGNITION",ISCAS13.

2012

• Dong Wang, Javier Tejedor "Heterogeneous convolutive non-negative sparse coding",interspeech 2012.

• Chao Liu, Dong Wang "N-gram indexing for spoken term detection",interspeech 2012.

• Ravichander Vipperla, Juergen Geiger, Simon Bozonnet, Dong Wang, Nicholas Evans, Bjoern Schuller, Gerhard Rigoll, "Speech overlap detection and attribution using convolutive non-negative sparse coding", ICASSP 2012.

• Huan Zhao, Yunqing Xia, Raymond Y. K. Lau, Yi Liu. Word Sentiment Polarity disambiguation based on Opinion level context. In ICMLC 2012 IWWIP workshop.

• Yunqing Xia, Guoyu Tang, Peng Jin, Xia Yang. CLTC: A Chinese-English Cross-lingual Topic Corpus. LREC 2012.

• Erik Cambria, Yunqing Xia, Amir Hussain. Affective Common Sense Knowledge Acquisition for Sentiment Analysis. LREC 2012.

• Chao Zhang, Yi Liu, Yunqing Xia, Chin-Hui Lee. Discriminative Dynamic Gaussian Mixture Selection with Enhanced Robustness and Performance for Multi-Accent Speech Recognition. ICASSP 2012.

2011

• Chao Zhang, Yi Liu, Yunqing Xia, Thomas Fang Zheng, Jesper Olsen, JiLei Tian: Reliable accent specific unit generation with dynamic Gaussian mixture selection for multi-accent speech recognition. ICME 2011: 1-6

• Jianfeng Zhang, Yunqing Xia, Bin Ma, Jianmin Yao, and Yu Hong. Thread Cleaning and Merging for Microblog Topic Detection. Proceedings of the 5th International Joint Conference on Natural Language Processing, pages 589–597, Chiang Mai, Thailand, November 8 – 13, 2011.

• Guoyu Tang, Yunqing Xia, Min Zhang, Haizhou Li, Fang Zheng. CLGVSM: Adapting Generalized Vector Space Model to Cross-lingual Document Clustering. Proceedings of the 5th International Joint Conference on Natural Language Processing, pages 580–588, Chiang Mai, Thailand, November 8 – 13, 2011.

• Yunqing Xia, Yonggang Zhang and Jianmin Yao. 2011. Co-clustering Sentences and Terms for Multi-document Summarization. Proc. of CICling’2011(II):339-352. Tokyo, Japan, February 20-26, 2011

• Yunqing Xia, Taotao Zhao, Jianmin Yao, and Peng Jin. 2011. Measuring Chinese-English Cross-Lingual Word Similarity with HowNet and Parallel Corpus. Proc. of CICling’2011(II):221-233. Tokyo, Japan, February 20-26, 2011

Patents

• 王军,王东,邬晓钧,郑方, "基于模型顺序自适应技术的说话人确认系统创建方法", 专利申请号：2013101390965, 公布日期: 2013.07.31

• 刘荣,王东,郑方, "基于分布式神经网络的语言模型训练方法及其系统", 专利申请号：2014100679169， 公布日期：2014.05.21

Others