121 |
an open source toolkit for parsing-based machine translation
|
|
|
|
In: http://www.mt-archive.info/WMT-2009-Li-1.pdf
|
|
BASE
|
|
Show details
|
|
122 |
Demonstration of Joshua: An Open Source Toolkit for Parsing-based Machine Translation ∗
|
|
|
|
In: http://cs.jhu.edu/~juri/pdf/joshua-acl-2009.pdf
|
|
BASE
|
|
Show details
|
|
123 |
WS96 Project Report Automatic Learning of Word Pronunciation from Data
|
|
|
|
In: http://www-speech.sri.com/papers/ws96-pronunciation.ps.gz
|
|
BASE
|
|
Show details
|
|
124 |
Revisiting the Case for Explicit Syntactic Information in Language Models
|
|
|
|
In: http://www.cs.jhu.edu/~mdredze/publications/naacl2012_ngram_workshop.pdf
|
|
BASE
|
|
Show details
|
|
125 |
Stochastic pronunciation modelling from hand-labelled phonetic
|
|
|
|
In: http://mi.eng.cam.ac.uk/reports/svr-ftp/nock_specom99.pdf
|
|
BASE
|
|
Show details
|
|
126 |
A KEYWORD SEARCH SYSTEM USING OPEN SOURCE SOFTWARE
|
|
|
|
In: http://www.clsp.jhu.edu/%7Eguoguo/papers/slt2014_babel_system_paper.pdf
|
|
BASE
|
|
Show details
|
|
127 |
e38 J Clin Exp Dent. 2010;2(1):e38-42. Clinical Implications and Outcome of Dry Storage of Avulsed Teeth. Journal section: Oral Medicine and Pathology doi:10.4317/jced.2.e38 Publication Types
|
|
|
|
In: http://www.medicinaoral.com/odo/volumenes/v2i1/jcedv2i1p38.pdf
|
|
BASE
|
|
Show details
|
|
128 |
Estimating Document Frequencies in a Speech Corpus
|
|
|
|
In: http://www.clsp.jhu.edu/%7Edamianos/asru11_df_stats.pdf
|
|
BASE
|
|
Show details
|
|
129 |
Adapting n-gram Maximum Entropy Language Models with Conditional Entropy Regularization
|
|
|
|
In: http://www.cs.jhu.edu/%7Emdredze/publications/2011_asru_semisupervised_adaptation.pdf
|
|
BASE
|
|
Show details
|
|
130 |
Unsupervised Estimation of the Language Model Scaling Factor
|
|
|
|
In: http://www.clsp.jhu.edu/%7Ecwhite/papers/interspeech_09_sslmsf.pdf
|
|
BASE
|
|
Show details
|
|
131 |
[dsp EDUCATION] Research Developments and Directions in Speech Recognition and Understanding, Part 1
|
|
|
|
In: http://groups.csail.mit.edu/sls/publications/2009/Minds-1-2009.pdf
|
|
BASE
|
|
Show details
|
|
132 |
HYPOTHESIS RANKING AND TWO-PASS APPROACHES FOR MACHINE TRANSLATION SYSTEM COMBINATION ∗
|
|
|
|
In: http://www.clsp.jhu.edu/~damianos/Karakos_et_al_ICASSP10.pdf
|
|
BASE
|
|
Show details
|
|
133 |
[dsp EDUCATION] Research Developments and Directions in Speech Recognition and Understanding, Part 1
|
|
|
|
In: http://research.microsoft.com/pubs/80528/SPM-MINDS-I.pdf
|
|
BASE
|
|
Show details
|
|
134 |
Maximum Entropy Techniques for Exploiting Syntactic, Semantic and Collocational Dependencies in Language Modeling
|
|
|
|
In: http://www.cs.jhu.edu/~junwu/cslpaper.ps
|
|
BASE
|
|
Show details
|
|
135 |
Unsupervised Arabic Dialect Adaptation with Self-Training
|
|
|
|
In: http://www.clsp.jhu.edu/people/snovotne/papers/novotney_interspeech11.pdf
|
|
BASE
|
|
Show details
|
|
137 |
Original Research Article Awareness and Knowledge of Autism Spectrum Disorders among Primary
|
|
|
|
In: http://www.ejmanager.com/mnstemps/107/107-1398678367.pdf
|
|
BASE
|
|
Show details
|
|
138 |
z Raytheon BBN
|
|
|
|
In: http://www.cs.jhu.edu/~alopez/papers/iwslt2013-post-etal.pdf
|
|
BASE
|
|
Show details
|
|
139 |
SOME INSIGHTS FROM TRANSLATING CONVERSATIONAL TELEPHONE SPEECH
|
|
|
|
In: http://cs.jhu.edu/~post/papers/kumar2013some.pdf
|
|
BASE
|
|
Show details
|
|
140 |
z Raytheon BBN
|
|
|
|
In: http://hltcoe.jhu.edu/uploads/publications/papers/14701_slides.pdf
|
|
Abstract:
Research into the translation of the output of automatic speech recognition (ASR) systems is hindered by the dearth of datasets developed for that explicit purpose. For Spanish-English translation, in particular, most parallel data available exists only in vastly different domains and registers. In order to support research on cross-lingual speech applications, we introduce the Fisher and Callhome Spanish-English Speech Translation Corpus, supplementing existing LDC audio and transcripts with (a) ASR 1-best, lattice, and oracle output pro-duced by the Kaldi recognition system and (b) English trans-lations obtained on Amazon’s Mechanical Turk. The result is a four-way parallel dataset of Spanish audio, transcrip-tions, ASR lattices, and English translations of approximately 38 hours of speech, with defined training, development, and held-out test sets. We conduct baseline machine translation experiments us-ing models trained on the provided training data, and validate the dataset by corroborating a number of known results in the field, including the utility of in-domain (information, conver-sational) training data, increased performance translating lat-tices (instead of recognizer 1-best output), and the relation-ship between word error rate and BLEU score. 1.
|
|
URL: http://hltcoe.jhu.edu/uploads/publications/papers/14701_slides.pdf http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.644.5234
|
|
BASE
|
|
Hide details
|
|
|
|