Publications
601.
White, Chris; Khudanpur, Sanjeev; Baker, J.
An Investigation of Acoustic Models for Multilingual Code-Switching Proceedings Article
In: International Speech Communication Association (INTERSPEECH), 2008.
@inproceedings{lrgqjavn,
title = {An Investigation of Acoustic Models for Multilingual Code-Switching},
author = {White, Chris and Khudanpur, Sanjeev and J. Baker},
url = {http://www.isca-speech.org/archive/interspeech_2008/i08_2691.html},
year = {2008},
date = {2008-01-01},
booktitle = {International Speech Communication Association (INTERSPEECH)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
602.
Karakos, D.; Khudanpur, S.; Marchette, D.; Papamarcou, A.; Priebe, C.
On the Minimization of Concave Information Functionals for Unsupervised Classification via Decision Trees Journal Article
In: pp. 975–984, 2008.
@article{karakos2008on,
title = {On the Minimization of Concave Information Functionals for Unsupervised Classification via Decision Trees},
author = {D. Karakos and S. Khudanpur and D. Marchette and A. Papamarcou and C. Priebe},
url = {http://ac.els-cdn.com/S0167715207003501/1-s2.0-S0167715207003501-main.pdf?_tid=485f80aa-c979-11e3-a142-00000aacb35d&acdnat=1398101029_3a9a6c0985e253d80353a41db88a66b2},
year = {2008},
date = {2008-01-01},
pages = {975--984},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
603.
Sivaram, Garimella; Hermansky, Hynek
Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASR Proceedings Article
In: 11th International Conference on Text, Speech and Dialogue (TSD), 2008.
@inproceedings{sivaram:08,
title = {Emulating Temporal Receptive Fields of Higher Level Auditory Neurons for ASR},
author = {Garimella Sivaram and Hermansky, Hynek},
year = {2008},
date = {2008-01-01},
booktitle = {11th International Conference on Text, Speech and Dialogue (TSD)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
604.
Priebe, C.; Wallis, W.
On the Anomalous Behaviour of a Class of Locality Statistics Journal Article
In: pp. 2034–2037, 2008.
@article{priebe2008on,
title = {On the Anomalous Behaviour of a Class of Locality Statistics},
author = {C. Priebe and W. Wallis},
year = {2008},
date = {2008-01-01},
pages = {2034--2037},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
605.
Marchette, D.; Priebe, Carey
Predicting Unobserved Links in Incompletely Observed Networks Journal Article
In: pp. 1373–1386, 2008.
@article{marchette2008predicting,
title = {Predicting Unobserved Links in Incompletely Observed Networks},
author = {D. Marchette and Priebe, Carey},
url = {http://ac.els-cdn.com/S0167947307001193/1-s2.0-S0167947307001193-main.pdf?_tid=adfb89e0-c659-11e3-82c1-00000aacb35d&acdnat=1397757602_82b55b823de03e51151041df6fca0c29},
year = {2008},
date = {2008-01-01},
pages = {1373--1386},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
606.
McNamee, Paul; Mayfield, James
N-gram Morphemes for Retrieval Proceedings Article
In: Working Notes for the Cross Language Evaluation Forum (CLEF), 2007.
@inproceedings{g41s3wqo,
title = {N-gram Morphemes for Retrieval},
author = {McNamee, Paul and Mayfield, James},
url = {http://www.clef-campaign.org/2007/working_notes/mcnameeCLEF2007.pdf},
year = {2007},
date = {2007-01-01},
booktitle = {Working Notes for the Cross Language Evaluation Forum (CLEF)},
abstract = {Stemming, an approximation to morphological analysis, is a commonly
used technique to improve performance in information retrieval systems.
In the MorphoChallenge 2007 evaluation we applied a simple zero-knowledge
technique that is based on frequency counts rather than machine learning.
Our method is based on substituting a single fixed-length substring
for each word that appears in documents or queries. We hope to discover
whether this method, which has been used in previous IR evaluations
with good effect, will be as effective for the information retrieval
task as the unsupervised methods used by other participants. It should
be emphasized that out submission was not a credible attempt to learn
morphology and thus is not expected to perform well in the morphology
induction task.},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Stemming, an approximation to morphological analysis, is a commonly
used technique to improve performance in information retrieval systems.
In the MorphoChallenge 2007 evaluation we applied a simple zero-knowledge
technique that is based on frequency counts rather than machine learning.
Our method is based on substituting a single fixed-length substring
for each word that appears in documents or queries. We hope to discover
whether this method, which has been used in previous IR evaluations
with good effect, will be as effective for the information retrieval
task as the unsupervised methods used by other participants. It should
be emphasized that out submission was not a credible attempt to learn
morphology and thus is not expected to perform well in the morphology
induction task.
used technique to improve performance in information retrieval systems.
In the MorphoChallenge 2007 evaluation we applied a simple zero-knowledge
technique that is based on frequency counts rather than machine learning.
Our method is based on substituting a single fixed-length substring
for each word that appears in documents or queries. We hope to discover
whether this method, which has been used in previous IR evaluations
with good effect, will be as effective for the information retrieval
task as the unsupervised methods used by other participants. It should
be emphasized that out submission was not a credible attempt to learn
morphology and thus is not expected to perform well in the morphology
induction task.
607.
Irvine, Ann; Callison-Burch, Chris
Using Comparable Corpora to Adapt MT Models to New Domains Proceedings Article
In: Proceedings of the ACL Workshop on Statistical Machine Translation (WMT), 0000.
@inproceedings{irvine-callisonburch-wmt14,
title = {Using Comparable Corpora to Adapt MT Models to New Domains},
author = {Irvine, Ann and Callison-Burch, Chris},
url = {http://www.cs.jhu.edu/~anni/papers/irvineCCB_wmt14.pdf},
booktitle = {Proceedings of the ACL Workshop on Statistical Machine Translation (WMT)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
608.
Xu, Tan; McNamee, Paul; Oard, Doug
HLTCOE at TREC 2013: Temporal Summarization
0000.
@{b,
title = {HLTCOE at TREC 2013: Temporal Summarization},
author = {Xu, Tan and McNamee, Paul and Oard, Doug},
abstract = {Our team submitted runs for the first running
of the TREC Temporal Summarization
track. We focused on the Sequential Update
Summarization task. This task involves
simulating processing a temporally ordered
stream of over 1 billion documents to identify
sentences that are relevant to a specific
breaking news stories which contain new
and important content. In this paper, we describe
our approach and evaluation results.},
keywords = {},
pubstate = {published},
tppubtype = {}
}
Our team submitted runs for the first running
of the TREC Temporal Summarization
track. We focused on the Sequential Update
Summarization task. This task involves
simulating processing a temporally ordered
stream of over 1 billion documents to identify
sentences that are relevant to a specific
breaking news stories which contain new
and important content. In this paper, we describe
our approach and evaluation results.
of the TREC Temporal Summarization
track. We focused on the Sequential Update
Summarization task. This task involves
simulating processing a temporally ordered
stream of over 1 billion documents to identify
sentences that are relevant to a specific
breaking news stories which contain new
and important content. In this paper, we describe
our approach and evaluation results.
609.
Irvine, Ann; Callison-Burch, Chris
Hallucinating Phrase Translations for Low Resource MT Proceedings Article
In: Proceedings of the Conference on Computational Natural Language Learning (CoNLL), 0000.
@inproceedings{irvine-callisonburch-conll14,
title = {Hallucinating Phrase Translations for Low Resource MT},
author = {Irvine, Ann and Callison-Burch, Chris},
url = {http://www.cs.jhu.edu/~anni/papers/irvineCCB_Hallucinating_CoNLL_14.pdf},
booktitle = {Proceedings of the Conference on Computational Natural Language Learning (CoNLL)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
610.
Hermansky, Hynek; Variani, Ehsan; Peddinti, Vijayaditya
Mean Temporal Distance: Predicting ASR Error from Temporal Properties of Speech
0000.
@{b,
title = {Mean Temporal Distance: Predicting ASR Error from Temporal Properties of Speech},
author = {Hynek Hermansky and Ehsan Variani and Vijayaditya Peddinti},
url = {http://ieeexplore.ieee.org/xpl/articleDetails.jsp?tp=&arnumber=6639105&queryText%3DMean+Temporal+Distance%3A+Predicting+ASR+Error+from+Temporal+Properties+of+Speech},
pages = {7423 - 7426},
publisher = {IEEE},
address = {Vancouver, BC},
abstract = {Extending previous work on prediction of phoneme recognition error from unlabeled data that were corrupted by unpredictable factors, the current work investigates a simple but effective method of estimating ASR performance by computing a function M(Δt), which represents the mean distance between speech feature vectors evaluated over certain finite time interval, determined as a function of temporal distance Δt between the vectors. It is shown that M(Δt) is a function of signal-to-noise ratio of speech signal. Comparing M(Δt) curves, derived on data used for training of the classifier, and on test utterances, allows for predicting error on the test data. Another interesting observation is that M(Δt) remains approximately constant, as temporal separation Δt exceeds certain critical interval (about 200 ms), indicating the extent of coarticulation in speech sounds.},
keywords = {},
pubstate = {published},
tppubtype = {}
}
Extending previous work on prediction of phoneme recognition error from unlabeled data that were corrupted by unpredictable factors, the current work investigates a simple but effective method of estimating ASR performance by computing a function M(Δt), which represents the mean distance between speech feature vectors evaluated over certain finite time interval, determined as a function of temporal distance Δt between the vectors. It is shown that M(Δt) is a function of signal-to-noise ratio of speech signal. Comparing M(Δt) curves, derived on data used for training of the classifier, and on test utterances, allows for predicting error on the test data. Another interesting observation is that M(Δt) remains approximately constant, as temporal separation Δt exceeds certain critical interval (about 200 ms), indicating the extent of coarticulation in speech sounds.
611.
Irvine, Ann; Langfus, Joshua; Callison-Burch, Chris
The American Local News Corpus Proceedings Article
In: Proceedings of the Language Resources and Evaluation Conference (LREC), 0000.
@inproceedings{irvine-etal-lrec14,
title = {The American Local News Corpus},
author = {Irvine, Ann and Joshua Langfus and Callison-Burch, Chris},
url = {http://www.cs.jhu.edu/~anni/papers/alnc_lrec14.pdf},
booktitle = {Proceedings of the Language Resources and Evaluation Conference (LREC)},
keywords = {},
pubstate = {published},
tppubtype = {inproceedings}
}
Sorry, no publications matched your criteria.
Upcoming Events
There are no upcoming events.
Archived COE News
- HLTCOE Principal Investigator Carey Priebe honored for contributing to one of National Geographic’s seven most inspiring medical breakthroughs of 2023.
- HLTCOE and JHU Researchers Supporting CHIME7 Workshop and Challenges
- 2023 North American Computational Linguistics Open Competition to be hosted at HLTCOE
- Dr. Zachary Lubberts Joins HLTCOE Research Staff
- Dr. Reno Kriz Joins the HLTCOE
