Please note: This is a beta version of the new dblp website.
You can find the classic dblp view of this page here.
You can find the classic dblp view of this page here.
Xiaodong He
2010 – today
- 2013
[j8]Xiaodong He, Li Deng: Speech-Centric Information Processing: An Optimization-Oriented Approach. Proceedings of the IEEE 101(5): 1116-1135 (2013)- [c30]Hongning Wang, Yang Song, Ming-Wei Chang, Xiaodong He, Ryen W. White, Wei Chu: Learning to extract cross-session search tasks. WWW 2013: 1353-1364
- [c29]Ryen W. White, Wei Chu, Ahmed Hassan, Xiaodong He, Yang Song, Hongning Wang: Enhancing personalized search by mining and modeling task behavior. WWW 2013: 1411-1420
- 2012
- [c28]Xiaodong He, Li Deng: Maximum Expected BLEU Training of Phrase and Lexicon Translation Models. ACL (1) 2012: 292-301
- [c27]Jianfeng Gao, Shasha Xie, Xiaodong He, Alnur Ali: Learning Lexicon Models from Search Logs for Query Expansion. EMNLP-CoNLL 2012: 666-676
- [c26]Amittai Axelrod, Xiaodong He, Li Deng, Alex Acero, Mei-Yuh Hwang: New methods and evaluation experiments on translating TED talks in the IWSLT benchmark. ICASSP 2012: 4945-4948
- [c25]Gökhan Tür, Li Deng, Dilek Hakkani-Tür, Xiaodong He: Towards deeper understanding: Deep convex networks for semantic utterance classification. ICASSP 2012: 5045-5048
- [c24]Xiaodong He, Li Deng: Optimization in speech-centric information processing: Criteria and techniques. ICASSP 2012: 5241-5244
- [c23]Li Deng, Gökhan Tür, Xiaodong He, Dilek Z. Hakkani-Tür: Use of kernel deep convex networks and end-to-end learning for spoken language understanding. SLT 2012: 210-215
- 2011
- [j7]Xiaodong He, Li Deng: Speech Recognition, Machine Translation, and Speech Translation - A Unified Discriminative Learning Paradigm [Lecture Notes]. IEEE Signal Process. Mag. 28(5): 126-133 (2011)
- [c22]Amittai Axelrod, Xiaodong He, Jianfeng Gao: Domain Adaptation via Pseudo In-Domain Data Selection. EMNLP 2011: 355-362
- [c21]Yaodong Zhang, Li Deng, Xiaodong He, Alex Acero: A novel decision function and the associated decision-feedback learning for speech translation. ICASSP 2011: 5608-5611
- [c20]Xiaodong He, Li Deng, Alex Acero: Why word error rate is not a good metric for speech recognizer training for the speech translation task? ICASSP 2011: 5632-5635
- [c19]
- 2010
- [j6]Xiaodong He, Li Deng, Roland Kuhn, Helen M. Meng, Samy Bengio: Introduction to the Issue on Statistical Learning Methods for Speech and Language Processing. J. Sel. Topics Signal Processing 4(6): 913-916 (2010)
- [c18]Jianfeng Gao, Xiaodong He, Jian-Yun Nie: Clickthrough-based translation models for web search: from word models to phrase models. CIKM 2010: 1139-1148
2000 – 2009
- 2009
- [j5]Xiaodong He, Mei Yang, Jianfeng Gao, Patrick Nguyen, Robert Moore: Improved Monolingual Hypothesis Alignment for Machine Translation System Combination. ACM Trans. Asian Lang. Inf. Process. 8(2) (2009)
- [c17]Chi-Ho Li, Xiaodong He, Yupeng Liu, Ning Xi: Incremental HMM Alignment for MT System Combination. ACL/IJCNLP 2009: 949-957
- [c16]Xiaodong He, Kristina Toutanova: Joint Optimization for Machine Translation System Combination. EMNLP 2009: 1202-1211
- [c15]Yong Zhao, Xiaodong He: Using N-gram based Features for Machine Translation System Combination. HLT-NAACL (Short Papers) 2009: 205-208
- 2008
- [b1]Xiaodong He, Li Deng: Discriminative Learning for Speech Recognition: Theory and Practice. Synthesis Lectures on Speech and Audio Processing, Morgan & Claypool Publishers 2008
- [j4]Dong Yu, Li Deng, Xiaodong He, Alex Acero: Large-margin minimum classification error training: A theoretical risk minimization perspective. Computer Speech & Language 22(4): 415-429 (2008)
- [c14]Xiaodong He, Mei Yang, Jianfeng Gao, Patrick Nguyen, Robert Moore: Indirect-HMM-based Hypothesis Alignment for Combining Outputs from Machine Translation Systems. EMNLP 2008: 98-107
- 2007
- [j3]Xiaodong He, Yunxin Zhao: Prior knowledge guided maximum expected likelihood based model selection and adaptation for nonnative speech recognition. Computer Speech & Language 21(2): 247-265 (2007)
- [j2]Xiaodong He, Li Deng: A new look at discriminative training for hidden Markov models. Pattern Recognition Letters 28(11): 1285-1294 (2007)
- [c13]Qian Qian, Xiaodong He, Li Deng: Phone-discriminating minimum classification error (p-MCE) training for phonetic recognition. INTERSPEECH 2007: 2073-2076
- 2006
- [c12]Xin Lei, Jon Hamaker, Xiaodong He: Robust feature space adaptation for telephony speech recognition. INTERSPEECH 2006
- [c11]Dong Yu, Li Deng, Xiaodong He, Alex Acero: Use of incrementally regulated discriminative margins in MCE training for speech recognition. INTERSPEECH 2006
- 2003
- [j1]Xiaodong He, Yunxin Zhao: Fast model selection based speaker adaptation for nonnative speech. IEEE Transactions on Speech and Audio Processing 11(4): 298-307 (2003)
- [c10]
- [c9]Wu Chou, Xiaodong He: Maximum a posteriori linear regression (MAPLR) variance adaptation for continuous density HMMS. INTERSPEECH 2003
- [c8]Xiaodong He, Wu Chou: Minimum classification error (MCE) model adaptation of continuous density HMMS. INTERSPEECH 2003
- 2002
- [c7]Xiaodong He, Yunxin Zhao: Fast model adaptation and complexity selection for nonnative English speakers. ICASSP 2002: 577-580
- [c6]Xiaodong He, Yunxin Zhao: Maximum expected likelihood based model selection and adaptation for nonnative English speakers. INTERSPEECH 2002
- 2001
- [c5]Xiaodong He, Yunxin Zhao: Model complexity optimization for nonnative English speakers. INTERSPEECH 2001: 1461-1464
- 2000
- [c4]Yunxin Zhao, Xiao Zhang, Xiaodong He, Laura Schopp: A combined adaptive and decision tree based speech separation technique for telemedicine applications. INTERSPEECH 2000: 795-798
1990 – 1999
- 1999
- [c3]Xiaodong He, Jian Liu, Jianlai Zhou, Tiecheng Yu: Research on speech units modeling in continuous speech recognition. EUROSPEECH 1999
- [c2]Jian Liu, Xiaodong He, Fuyuan Mo, Tiecheng Yu: Study on tone classification of Chinese continuous speech in speech recognition system. EUROSPEECH 1999
- [c1]Jianlai Zhou, Xiaodong He, Tiecheng Yu, Fuyuan Mo: A new hybrid structure of speech recognizer based on HMM and neural network. EUROSPEECH 1999
Coauthor Index
data released under the ODC-BY 1.0 license. See also our legal information page
last updated on 2013-05-26 22:02 CEST by the dblp team