Home
Catalogue search
Refine your search:
Keyword:
ACCURACY (9)
Linguistics (6)
VARIABLES (6)
*SPEECH RECOGNITION (3)
Cybernetics (3)
LEARNING (3)
RANDOM VARIABLES (3)
RATES (3)
SPEECH (3)
*ACOUSTIC SIGNALS (2)
more
Creator / Publisher:
BOSTON UNIV MA (2)
AIR FORCE INST OF TECH WRIGHT-PATTERSON AFB OH SCHOOL OF ENGINEERING (1)
Cohen, Michael (1)
Dosher, Barbara A. (1)
Easterly, Jill A. (1)
Emonts, Michael (1)
Gatewood, Paul (1)
Grossberg, Stephen (1)
ILLINOIS UNIV AT URBANA-CHAMPAIGN DEPT OF COMPUTER SCIENCE (1)
Jairam, Arvind (1)
more
Year
Medium
Type
BLLDB-Access
Search in the Catalogues and Directories
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
AND
OR
AND NOT
All fields
Title
Creator / Publisher
Keyword
Year
Sort by
creator [A → Z]
'
creator [Z → A]
'
publishing year ↑ (asc)
'
publishing year ↓ (desc)
'
title [A → Z]
'
title [Z → A]
'
Simple Search
Hits 1 – 9 of 9
1
Experimental Facility for Measuring the Impact of Environmental Noise and Speaker Variation on Speech-to-Speech Translation Devices
Jones, Douglas A.
;
Jairam, Arvind
;
Shen, Wade
...
In: DTIC (2006)
BASE
Show details
2
Sparse Forward-Backward for Fast Training of Conditional Random Fields
Sutton, Charles
;
Pal, Chris
;
McCallum, Andrew
In: DTIC (2006)
Abstract:
Complex tasks in speech and language processing often include random variables with large state spaces, both in speech tasks that involve predicting words and phonemes, and in joint processing of pipelined systems in which the state space can be the labeling of an entire sequence. In large state spaces, however, discriminative training can be expensive, because it often requires many calls to forward-backward. Beam search is a standard heuristic for controlling complexity during Viterbi decoding, but during forward-backward, standard beam heuristics can be dangerous, as they can make training unstable. The authors introduce sparse forward-backward, a variational perspective on beam methods that uses an approximating mixture of Kronecker delta functions. This motivates a novel minimum-divergence beam criterion based on minimizing Kullback-Leibler (KL) divergence between the respective marginal distributions. This beam selection approach is not only more efficient for Viterbi decoding, but also more stable within sparse forward-backward training. For a standard text-to-speech problem, they reduce CRF training time fourfold -- from over a day to 6 hours -- with no loss in accuracy. ; Sponsored in part by the Central Intelligence Agency, the National Security Agency, and the National Science Foundation. The original document contains color images.
Keyword:
*DECODING
;
*EXPERT SYSTEMS
;
*LANGUAGE
;
*LANGUAGE PROCESSING
;
*PROCESSING
;
*SPARSE FORWARD-BACKWARD
;
*SPEECH ANALYSIS
;
*TRAINING
;
*VITERBI DECODING
;
ACCURACY
;
BEAM SEARCH
;
CRF TRAINING
;
CRF(CONDITIONAL RANDOM FIELDS)
;
Cybernetics
;
DELTA FUNCTIONS
;
DISCRETE DISTRIBUTION
;
ESTIMATES
;
HEURISTIC METHODS
;
HIDDEN MARKOV MODELS
;
LEARNING
;
Linguistics
;
MARKOV PROCESSES
;
MATHEMATICAL PREDICTION
;
MAX-PRODUCT INFERENCE
;
MINIMUM-DIVERGENCE BEAM
;
NETTALK DATA SET
;
PHONEMES
;
RANDOM VARIABLES
;
SPEECH PROCESSING
;
Statistics and Probability
;
SUM-PRODUCT INFERENCE
;
TIME SAVINGS
URL:
http://oai.dtic.mil/oai/oai?&verb=getRecord&metadataPrefix=html&identifier=ADA443633
http://www.dtic.mil/docs/citations/ADA443633
BASE
Hide details
3
A Linear Programming Formulation for Global Inference in Natural Language Tasks
Roth, Dan
;
Yih, Wen-tau
In: DTIC (2004)
BASE
Show details
4
High-Order Modeling Techniques for Continuous Speech Recognition.
Ostendorf, Mari
In: DTIC AND NTIS (1995)
BASE
Show details
5
A Self-Organizing Neural Network Architecture for Auditory and Speech Perception with Applications to Acoustic and Other Temporal Prediction Problems
Grossberg, Stephen
;
Cohen, Michael
In: DTIC AND NTIS (1994)
BASE
Show details
6
Coherence and Usability of an Environmental Impact Statement
Easterly, Jill A.
In: DTIC AND NTIS (1994)
BASE
Show details
7
Word and Subword Modelling in a Segment-Based HMM Word Spotter Using a Data Analytic Approach
Marcus, Jeffrey N.
In: DTIC AND NTIS (1992)
BASE
Show details
8
The Effect of Three Variables on Synthetic Speech Intelligibility in Noisy Environments
Munlin, Joyce C.
In: DTIC AND NTIS (1990)
BASE
Show details
9
The Kinetic Depth Effect and Identification of Shape
Sperling, George
;
Landy, Michael S.
;
Dosher, Barbara A.
...
In: DTIC AND NTIS (1987)
BASE
Show details
Mobile view
All
Catalogues
UB Frankfurt Linguistik
0
IDS Mannheim
0
OLC Linguistik
0
UB Frankfurt Retrokatalog
0
DNB Subject Category Language
0
Institut für Empirische Sprachwissenschaft
0
Leibniz-Centre General Linguistics (ZAS)
0
Bibliographies
BLLDB
0
BDSL
0
IDS Bibliografie zur deutschen Grammatik
0
IDS Bibliografie zur Gesprächsforschung
0
IDS Konnektoren im Deutschen
0
IDS Präpositionen im Deutschen
0
IDS OBELEX meta
0
MPI-SHH Linguistics Collection
0
MPI for Psycholinguistics
0
Linked Open Data catalogues
Annohub
0
Online resources
Link directory
0
Journal directory
0
Database directory
0
Dictionary directory
0
Open access documents
BASE
9
Linguistik-Repository
0
IDS Publikationsserver
0
Online dissertations
0
Language Description Heritage
0
© 2013 - 2024 Lin|gu|is|tik
|
Imprint
|
Privacy Policy
|
Datenschutzeinstellungen ändern