1 |
A Hybrid Method for Opinion Finding Task (KUNLP at TREC 2008 Blog Track)
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
2 |
TREC 2008 at the University at Buffalo: Legal and Blog Track
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
4 |
KLE at TREC 2008 Blog Track: Blog Post and Feed Retrieval
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
6 |
Applying A Formal Language of Command and Control For Interoperability Between Systems
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
7 |
Automating Convoy Training Assessment to Improve Soldier Performance
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
8 |
Barriers, Bridges, and Progress in Cognitive Modeling for Military Applications
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
9 |
Odds of Successful Transfer of Low-level Concepts: A Key Metric for Bidirectional Speech-to-Speech Machine Translation in DARPA's TRANSTAC Program
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
11 |
Integrating a Natural Language Message Pre-Processor with UIMA
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
12 |
CSIR at TREC 2008 Expert Search Task: Modeling Expert Evidence in Expert Search
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
13 |
Support for the Annual Meeting (30th) of the Cognitive Science Society
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
14 |
Laboratory for Computational Cultural Dynamics
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
16 |
Natural Language Dialogue Architectures for Tactical Questioning Characters
|
|
|
|
In: DTIC (2008)
|
|
BASE
|
|
Show details
|
|
20 |
Empirical Properties of Multilingual Phone-To-Word Transduction
|
|
|
|
In: DTIC (2008)
|
|
Abstract:
This paper explores the error-robustness of phone-to-word transduction across a variety of languages. We implement a noisy channel model in which a phonetic input stream is corrupted by an error model, and then transduced back to words using the inverse error model and linguistic constraints. By controlling the error level, we are able to measure the sensitivity of different languages to degradation in the phonetic input stream. This analysis is carried further to measure the importance of each phone in each language individually. We study Arabic, Chinese, English, German and Spanish, and find that they behave similarly in this paradigm: in each case, a phone error produces about 1.4 word errors, and frequently incorrect phones matter slightly less than others. In the absence of phone errors, transduced word errors are still present, and we use the conditional entropy of words given phones to explain the observed behavior. ; See also ADM002091. Presented at the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008) held in Las Vegas, Nevada on March 30-April 4, 2008. Published in the Proceedidngs of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008) p4445-4448, 2008.
|
|
Keyword:
*MULTILINGUAL; *SPEECH RECOGNITION; *TRANSDUCTION; ASR(AUTOMATIC SPEECH RECOGNTION); DECODING; DEGRADATION; Electrical and Electronic Equipment; ENTROPY; ERRORS; INVERSION; Linguistics; MODELS; PHONETICS; SENSITIVITY; SYMPOSIA; WORDS(LANGUAGE)
|
|
URL: http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA509700 http://www.dtic.mil/docs/citations/ADA509700
|
|
BASE
|
|
Hide details
|
|
|
|