DE eng

Search in the Catalogues and Directories

Page: 1 2
Hits 1 – 20 of 40

1
Using word embedding for bio-event extraction
Li, Chen; Song, Runqing; Liakata, Maria. - : Association for Computational Linguistics, 2015
BASE
Show details
2
Is Cholesterol Sulfate Deficiency a Common Factor in Preeclampsia, Autism, and Pernicious Anemia?
In: MDPI Publishing (2012)
BASE
Show details
3
Utilizing Review Summarization in a Spoken Recommendation System
In: MIT web domain (2010)
BASE
Show details
4
Dialogue-Oriented Review Summary Generation for Spoken Dialogue Recommendation Systems
In: MIT web domain (2010)
BASE
Show details
5
Speech-enabled card games for incidental vocabulary acquisition in a foreign language
In: Speech communication. - Amsterdam [u.a.] : Elsevier 51 (2009) 10, 1006-1023
BLLDB
OLC Linguistik
Show details
6
A two-pass approach for handling out-of-vocabulary words in a large vocabulary recognition task
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 21 (2007) 1, 206-218
BLLDB
OLC Linguistik
Show details
7
Automatic induction of language model data for a spoken dialogue system
In: Language resources and evaluation. - Dordrecht [u.a.] : Springer 40 (2006) 1, 25-46
BLLDB
Show details
8
Statistical modeling of phonological rules through linguistic hierarchies
In: Speech communication. - Amsterdam [u.a.] : Elsevier 46 (2005) 2, 204-216
BLLDB
OLC Linguistik
Show details
9
The use of subword linguistic modeling for multiple tasks in speech recognition
In: Speech communication. - Amsterdam [u.a.] : Elsevier 42 (2004) 3, 373-390
OLC Linguistik
Show details
10
The use of subword linguistic modeling for multiple tasks in speech recognition
In: Speech communication. - Amsterdam [u.a.] : Elsevier 42 (2004) 3-4, 373-390
BLLDB
Show details
11
Recognition confidence scoring and its use in speech understanding systems
In: Computer speech and language. - Amsterdam [u.a.] : Elsevier 16 (2002) 1, 49-68
OLC Linguistik
Show details
12
Interlingua-Based Broad-Coverage Korean-to-English Translation in CCLINC
In: DTIC (2001)
BASE
Show details
13
Ahierarchical duration model for speech recognition based on the ANGIEframework
In: Speech communication. - Amsterdam [u.a.] : Elsevier 27 (1999) 2, 113-134
OLC Linguistik
Show details
14
A hierarchical duration model for speech recognition based on the ANGIE framework
In: Speech communication. - Amsterdam [u.a.] : Elsevier 27 (1999) 2, 113-134
BLLDB
Show details
15
Comments on "Towards increasing speech recognition error rates" by H. Bourlard, H. Hermansky, and N. Morgan
Atal, Bishnu S. (Mitarb.); De Mori, Renato (Mitarb.); Flanagan, Jim (Mitarb.)...
In: Speech communication. - Amsterdam [u.a.] : Elsevier 18 (1996) 3, 233-255
BLLDB
Show details
16
Angie : a new framework for speech analysis based on morpho-phonological modelling
In: ICSLP <4, 1996, Philadelphia, Pa.>. Proceedings ; 1. - Wilmington, Del. : Applied Science and Engineering Laboratories (1996), 110-113
BLLDB
Show details
17
Reversible letter-to-sound/sound-to-letter generation based on parsing word morphology
In: Speech communication. - Amsterdam [u.a.] : Elsevier 18 (1996) 1, 47-63
BLLDB
Show details
18
Multilingual spoken-language understanding in the MIT voyager system
In: Speech communication. - Amsterdam [u.a.] : Elsevier 17 (1995) 1-2, 1-18
BLLDB
Show details
19
Spoken dialogue
Shirai, Katsuhiko (Hrsg.); Furui, Sadaoki (Hrsg.); Nagata, Masaaki (Mitarb.)...
In: Speech communication. - Amsterdam [u.a.] : Elsevier 15 (1994) 3-4, 189-365
BLLDB
Show details
20
Phonological Parsing for Bi-directional Letter-to-Sound/Sound-to-Letter Generation
In: DTIC (1994)
Abstract: In this paper, we describe a reversible letter-to-sound/sound to-letter generation system based on an approach which combines a rule-based formalism with data-driven techniques. We adopt a probabilistic parsing strategy to provide a hierarchical lexical analysis of a word, including information such as morphology, stress, syllabification, phonemics and graphemics. Long-distance constraints are propagated by enforcing local constraints throughout the hierarchy. Our training and testing corpora are derived from the high-frequency portion of the Brown Corpus (10,000 words), augmented with markers indicating stress and word morphology. We evaluated our performance based on an unseen test set. The percentage of nonparsable words for letter-to-sound and sound-to-letter generation were 6% and 5% respectively. Of the remaining words our system achieved a word accuracy of 71.8% and a phoneme accuracy of 92.5% for letter-to-sound generation, and a word accuracy of 55.8% and letter accuracy of 89.4% for sound-to-letter generation. We also compared our hierarchical approach with an alternative, single-layer approach to demonstrate how the hierarchy provides a parsimonious description for English orthographic-phonological regularities, while simultaneously attaining competitive generation accuracy. ; Supported in part by DARPA.
Keyword: *PARSERS; *WORDS(LANGUAGE); ACCURACY; COMPETITION; HIERARCHIES; INDICATORS; LEXICOGRAPHY; Linguistics; MARKERS; MORPHOLOGY; PHONETICS; PROBABILITY; STRATEGY; STRESSES; TEST SETS
URL: http://www.dtic.mil/docs/citations/ADA458591
http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA458591
BASE
Hide details

Page: 1 2

Catalogues
0
0
6
0
0
0
0
Bibliographies
17
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
20
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern