Sciweavers

2047 search results - page 163 / 410
» The limits of speech recognition
Sort
View
IUI
2005
ACM
14 years 3 months ago
How to wreck a nice beach you sing calm incense
A principal problem in speech recognition is distinguishing between words and phrases that sound similar but have different meanings. Speech recognition programs produce a list of...
Henry Lieberman, Alexander Faaborg, Waseem Daher, ...
INTERSPEECH
2010
13 years 4 months ago
Using a DBN to integrate sparse classification and GMM-based ASR
The performance of an HMM-based speech recognizer using MFCCs as input is known to degrade dramatically in noisy conditions. Recently, an exemplar-based noise robust ASR approach,...
Yang Sun, Jort F. Gemmeke, Bert Cranen, Louis ten ...
ICPR
2008
IEEE
14 years 4 months ago
Comparison of Particle Swarm Optimization and Genetic Algorithm for HMM training
Hidden Markov Model (HMM) is the dominant technology in speech recognition. The problem of optimizing model parameters is of great interest to the researchers in this area. The Ba...
Fengqin Yang, Changhai Zhang, Tieli Sun
CLIN
2001
13 years 11 months ago
Memory-Based Phoneme-to-Grapheme Conversion
In this paper, we describe a method to enhance the readability of out-of-vocabulary items (OOVs) in the textual output in a large vocabulary continuous speech recognition system. ...
Bart Decadt, Jacques Duchateau, Walter Daelemans, ...
DKE
2002
134views more  DKE 2002»
13 years 10 months ago
Spoken query processing for interactive information retrieval
It has long been recognised that interactivity improves the effectiveness of Information Retrieval systems. Speech is the most natural and interactive medium of communication and ...
Fabio Crestani