Commit ef5c11ac authored by Dan Povey's avatar Dan Povey
Browse files

Minor futher changes to paper.

git-svn-id: https://svn.code.sf.net/p/kaldi/code/sandbox/discrim@532 5e6a8d80-dfce-4ca6-a32a-6e07a63d50c8
parent 60d9207e
PAPER=icassp12
all: $(PAPER).pdf
cp $(PAPER).pdf ~/desktop/2012_icassp_semicont.pdf || true
ifeq ($(shell uname), Darwin)
$(PAPER).pdf: $(PAPER).tex $(PAPER).bbl
......@@ -9,7 +10,7 @@ $(PAPER).pdf: $(PAPER).tex $(PAPER).bbl
else
$(PAPER).pdf: $(PAPER).tex $(PAPER).bbl
pdflatex $(PAPER)
cp $(PAPER).pdf ~/desktop/2012_icassp_semicont.pdf || true
endif
......
......@@ -51,13 +51,12 @@ of transcribed speech.
This has led to a renewed interest in methods of reducing the number of parameters
while maintaining or extending the modeling capabilities of continuous models.
%
In this work, we compare classic and multiple-codebook semi-continuous models
that use full covariance matrices with continuous HMMs and subspace Gaussian mixture models.
%
Experiments using on the RM and WSJ corpora show that a semi-continuous system
can still yield competitive results while using fewer Gaussian components.
Our best semi-continous systems included full-covariance codebook Gaussians,
multiple codebooks, and smoothing of the weight parameters.
In this work, we compare classic and multiple-codebook semi-continuous models
using diagonal and full covariance matrices with continuous HMMs and subspace Gaussian
mixture models.
Experiments using on the RM and WSJ corpora show that while a classical semi-continous
system does not perform as well as a continuous one, multiple-codebook semi-continuous
systems can perform better, particular when using full-covariance Gaussians.
\end{abstract}
\begin{keywords}
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment