DE eng

Search in the Catalogues and Directories

Page: 1 2 3
Hits 41 – 52 of 52

41
The Effect of Bilingual Term List Size on Dictionary-Based Cross-Language Information Retrieval
In: DTIC (2006)
BASE
Show details
42
Effectively Using Syntax for Recognizing False Entailment
In: DTIC (2006)
BASE
Show details
43
Efficacy in Automated Language Translators
In: DTIC (2006)
BASE
Show details
44
Auditory Steady-State Response: Test-Retest Reliability
In: ETSU Faculty Works (2006)
BASE
Show details
45
An Analysis of Specware and Its Usefulness in the Verification of High Assurance Systems
In: DTIC (2006)
BASE
Show details
46
Dialogue Structure and Pronoun Resolution
In: DTIC (2006)
BASE
Show details
47
The 2005 AFRL/HEC One-Speaker Detection Systems
In: DTIC (2006)
Abstract: This paper describes the one-speaker detection systems submitted by AFRL/HEC for several of the training and testing conditions in the 2005 NIST Speaker Recognition Evaluation. For each condition, the overall system score was the weighted combination of scores from several component systems. The component systems were based on: mel-frequency cepstral coefficients (MFCCs) and (Gaussian mixture models (GMMs); MFCCs and phoneme-specific GMMs (PS-GMMs); linear-prediction-based cepstral coefficients (LPCCs) from closed-phase analysis; formant center frequencies, formant bandwidths, and fundamental frequency(FMBWFO); and word language modeling (WLM). The score combination was done using single-layer perceptrons, with the grouping of the component systems depending on the lengths of the training and testing files. For some of the testing and/or training conditions involving ten-second speech files, the system performance improved from the inclusion of the FMBWFO and LPCC systems, while the MFCC/PS-GMM system provided additional benefits in the one-conversation testing conditions involving larger amounts of training data. ; The original document contains color images. To be presented at the IEEE Odyssey Speaker and Language Recognition Workshop (2006) to be held in San Juan, Puerto Rico on 28-30 Jun 2006. Will be published in Proceedings of the IEEE Odyssey Speaker and Language Recognition Workshop (2006), cleared 17 Feb 2006 for public release.
Keyword: *CEPSTRUM TECHNIQUE; *DETECTION; *SPEECH RECOGNITION; *TEST AND EVALUATION; *TRAINING; BANDWIDTH; COEFFICIENTS; Command; COMPONENT REPORTS; Control and Communications Systems; Electricity and Magnetism; FREQUENCY; LP(LINEAR PREDICTIONS); MODELS; Numerical Mathematics; PHONEMES; SYMPOSIA; WEIGHTING FUNCTIONS; WLM(WORD LANGUAGE MODELING); WORDS(LANGUAGE); WUAFRL71840871
URL: http://www.dtic.mil/docs/citations/ADA445157
http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA445157
BASE
Hide details
48
A Methodology for End-to-End Evaluation of Arabic Document Image Processing Software
In: DTIC (2006)
BASE
Show details
49
Preferred overall loudness. I: Sound field presentation in the laboratory
BASE
Show details
50
Preferred overall loudness. II: Listening through hearing aids in field and laboratory tests
Smeds, Karolina; Keidser, Gitte; Zakis, Justin. - : Informa UK Limited, 2006
BASE
Show details
51
Lexical errors in young efl learners: how do they relate to proficiency measures?
In: Interlingüística, ISSN 1134-8941, Nº. 17, 2006, pags. 63-73 (2006)
BASE
Show details
52
STUDENTS' STRATEGIES FOR TAKING CLASSROOM TESTS
In: K@ta: A Biannual Publication on the Study of Language and Literature, Vol 8, Iss 2, Pp 127-136 (2006) (2006)
BASE
Show details

Page: 1 2 3

Catalogues
0
0
18
0
0
0
4
Bibliographies
32
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
16
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern