Sciweavers

2047 search results - page 153 / 410
» The limits of speech recognition
Sort
View
NAACL
2010
13 years 6 months ago
Contextual Information Improves OOV Detection in Speech
Out-of-vocabulary (OOV) words represent an important source of error in large vocabulary continuous speech recognition (LVCSR) systems. These words cause recognition failures, whi...
Carolina Parada, Mark Dredze, Denis Filimonov, Fre...
ICASSP
2010
IEEE
13 years 3 months ago
Unsupervised knowledge acquisition for Extracting Named Entities from speech
This paper presents a Named Entity Recognition (NER) method dedicated to process speech transcriptions. The main principle behind this method is to collect in an unsupervised way ...
Frédéric Béchet, Eric Charton
MLMI
2007
Springer
14 years 3 months ago
To Separate Speech
The PASCAL Speech Separation Challenge (SSC) is based on a corpus of sentences from the Wall Street Journal task read by two speakers simultaneously and captured with two circular ...
John W. McDonough, Ken'ichi Kumatani, Tobias Gehri...
ICASSP
2009
IEEE
14 years 3 months ago
The effectiveness of histogram equalization on environmental model adaptation
In this paper, we introduce a new histogram equalizationbased environmental model adaptation method for robust speech recognition in noise environments. The proposed method adapts...
Youngjoo Suh, Hoirin Kim
ICASSP
2008
IEEE
14 years 3 months ago
Exploiting temporal change of pitch in formant estimation
This paper considers the problem of obtaining an accurate spectral representation of speech formant structure when the voicing source exhibits a high fundamental frequency. Our wo...
Tao T. Wang, Thomas F. Quatieri