Sciweavers

775 search results - page 102 / 155
» Processing Self Corrections in a speech to speech system
Sort
View
AIIA
2005
Springer
13 years 9 months ago
Building a Wide Coverage Dynamic Grammar
Incremental processing is relevant for language modeling, speech recognition and language generation. In this paper we devise a dynamic version of Tree Adjoining Grammar (DVTAG) th...
Alessandro Mazzei, Vincenzo Lombardo
ICASSP
2009
IEEE
13 years 5 months ago
Volterra series for analyzing MLP based phoneme posterior estimator
We present a framework to apply Volterra series to analyze multilayered perceptrons trained to estimate the posterior probabilities of phonemes in automatic speech recognition. Th...
Joel Pinto, Garimella S. V. S. Sivaram, Hynek Herm...
ICASSP
2011
IEEE
12 years 11 months ago
Automatic Language Identification in music videos with low level audio and visual features
Automatic Language Identification (LID) in music has received significantly less attention than LID in speech. Here, we study the problem of LID in music videos uploaded on YouT...
Vijay Chandrasekhar, Mehmet Emre Sargin, David A. ...
MM
1996
ACM
120views Multimedia» more  MM 1996»
13 years 12 months ago
Negotiation for Automated Generation of Temporal Multimedia Presentations
Creating high-quality multimediapresentationsrequiresmuch skill, time, and effort. This is particularly true when temporal media, such as speech and animation, are involved. We de...
Mukesh Dalal, Steven Feiner, Kathleen McKeown, Shi...
ICASSP
2011
IEEE
12 years 11 months ago
Nonstationary and temporally correlated source separation using Gaussian process
Blind source separation (BSS) is a process to reconstruct source signals from the mixed signals. The standard BSS methods assume a fixed set of stationary source signals with the ...
Hsin-Lung Hsieh, Jen-Tzung Chien