1 |
Speech-Centric Information Processing: An Optimization-Oriented Approach
|
|
|
|
In: http://research.microsoft.com/pubs/179540/PIEEE_He_Deng_2013.pdf (20132)
|
|
BASE
|
|
Show details
|
|
2 |
Towards deeper understanding: Deep convex networks for semantic utterance classification,” ICASSP
|
|
|
|
In: http://research.microsoft.com/pubs/164624/5045.pdf (2012)
|
|
BASE
|
|
Show details
|
|
3 |
Speech-Centric Information Processing: An Optimization-Oriented Approach
|
|
|
|
In: http://research.microsoft.com/pubs/179540/ProcIEEE_He_deng_finalsub.pdf (2012)
|
|
BASE
|
|
Show details
|
|
4 |
The MSR System for IWSLT 2011 Evaluation
|
|
|
|
In: http://www.mt-archive.info/IWSLT-2011-He.pdf (2011)
|
|
BASE
|
|
Show details
|
|
5 |
The MSR System for IWSLT 2011 Evaluation
|
|
|
|
In: http://research.microsoft.com/pubs/163079/IWSLT2011_MSR_v04.pdf (2011)
|
|
Abstract:
This paper describes the Microsoft Research (MSR) system for the evaluation campaign of the 2011 international workshop on spoken language translation. The evaluation task is to translate TED talks (www.ted.com). This task presents two unique challenges: First, the underlying topic switches sharply from talk to talk. Therefore, the translation system needs to adapt to the current topic quickly and dynamically. Second, only a very small amount of relevant parallel data (transcripts of TED talks) is available. Therefore, it is necessary to perform accurate translation model estimation with limited data. In the preparation for the evaluation, we developed two new methods to attack these problems. Specifically, we developed an unsupervised topic modeling based adaption method for machine translation models. We also developed a discriminative training method to estimate parameters in the generative components of the translation models with limited data. Experimental results show that both methods improve the translation quality. Among all the submissions, ours achieves the best BLEU score in the machine translation Chinese-to-English track (MT_CE) of the IWSLT 2011 evaluation that we participated. 1.
|
|
URL: http://research.microsoft.com/pubs/163079/IWSLT2011_MSR_v04.pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.307.146
|
|
BASE
|
|
Hide details
|
|
6 |
Clickthrough-based translation models for web search: from word models to phrase models
|
|
|
|
In: http://www.iro.umontreal.ca/~nie/Publication/gao-cikm10.pdf (2010)
|
|
BASE
|
|
Show details
|
|
7 |
Joint Optimization for Machine Translation System Combination
|
|
|
|
In: http://www.mt-archive.info/EMNLP-2009-He.pdf (2009)
|
|
BASE
|
|
Show details
|
|
8 |
Joint optimization for machine translation system combination
|
|
|
|
In: http://research.microsoft.com/%7Exiaohe/publication/EMNLP2009_draft.pdf (2009)
|
|
BASE
|
|
Show details
|
|
9 |
Joint optimization for machine translation system combination
|
|
|
|
In: http://www.aclweb.org/anthology-new/D/D09/D09-1125.pdf (2009)
|
|
BASE
|
|
Show details
|
|
10 |
A novel learning method for hidden Markov models in speech and audio processing
|
|
|
|
In: http://research.microsoft.com/%7Exiaohe/publication/IEEE_MMSP06_p226.pdf (2006)
|
|
BASE
|
|
Show details
|
|
11 |
Maximum expected bleu training of phrase and lexicon translation models
|
|
|
|
In: http://www.aclweb.org/anthology/P/P12/P12-1031.pdf
|
|
BASE
|
|
Show details
|
|
12 |
Learning Lexicon Models from Search Logs for Query Expansion
|
|
|
|
In: http://www.research.microsoft.com/%7Ejfgao/paper/2012-papers/gao-et-al.emnlp2012.camera.v3.pdf
|
|
BASE
|
|
Show details
|
|
13 |
Learning Lexicon Models from Search Logs for Query Expansion
|
|
|
|
In: http://research.microsoft.com/pubs/166360/D12-1061.pdf
|
|
BASE
|
|
Show details
|
|
14 |
Why word error rate is not a good metric for speech recognizer training for the speech translation task
|
|
|
|
In: http://research.microsoft.com/pubs/144223/0005632.pdf
|
|
BASE
|
|
Show details
|
|
15 |
RECENT ADVANCES IN DEEP LEARNING FOR SPEECH RESEARCH AT MICROSOFT
|
|
|
|
In: http://research.microsoft.com/pubs/188864/ICASSP-2013-OverviewMSRDeepLearning.pdf
|
|
BASE
|
|
Show details
|
|
16 |
Phone-Discriminating Minimum Classification Error (P-MCE) Training for Phonetic Recognition
|
|
|
|
In: http://research.microsoft.com/%7Exiaohe/publication/interspeech07-PMCE.pdf
|
|
BASE
|
|
Show details
|
|
17 |
Model Complexity Optimization for Nonnative English Speakers
|
|
|
|
In: http://research.microsoft.com/%7Exiaohe/publication/EuroSph01_mel.pdf
|
|
BASE
|
|
Show details
|
|
18 |
A COMBINED ADAPTIVE AND DECISION TREE BASED SPEECH SEPARATION TECHNIQUE FOR TELEMEDICINE APPLICATIONS
|
|
|
|
In: http://research.microsoft.com/%7Exiaohe/publication/ICSLP00-TeleMed.pdf
|
|
BASE
|
|
Show details
|
|
19 |
PATRICK NGUYEN
|
|
|
|
In: http://www.research.microsoft.com/~jfgao/paper/talip2008_syscomb_final.pdf
|
|
BASE
|
|
Show details
|
|
20 |
A NOVEL DECISION FUNCTION AND THE ASSOCIATED DECISION-FEEDBACK LEARNING FOR SPEECH TRANSLATION
|
|
|
|
In: http://groups.csail.mit.edu/sls/publications/2011/Zhang1_ICASSP2011.pdf
|
|
BASE
|
|
Show details
|
|
|
|