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 PAPER=icassp12
all: $(PAPER).pdf all: $(PAPER).pdf
cp $(PAPER).pdf ~/desktop/2012_icassp_semicont.pdf || true
ifeq ($(shell uname), Darwin) ifeq ($(shell uname), Darwin)
$(PAPER).pdf: $(PAPER).tex $(PAPER).bbl $(PAPER).pdf: $(PAPER).tex $(PAPER).bbl
...@@ -9,7 +10,7 @@ $(PAPER).pdf: $(PAPER).tex $(PAPER).bbl ...@@ -9,7 +10,7 @@ $(PAPER).pdf: $(PAPER).tex $(PAPER).bbl
else else
$(PAPER).pdf: $(PAPER).tex $(PAPER).bbl $(PAPER).pdf: $(PAPER).tex $(PAPER).bbl
pdflatex $(PAPER) pdflatex $(PAPER)
cp $(PAPER).pdf ~/desktop/2012_icassp_semicont.pdf || true
endif endif
......
...@@ -51,13 +51,12 @@ of transcribed speech. ...@@ -51,13 +51,12 @@ of transcribed speech.
This has led to a renewed interest in methods of reducing the number of parameters 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. while maintaining or extending the modeling capabilities of continuous models.
% %
In this work, we compare classic and multiple-codebook semi-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. using diagonal and 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 Experiments using on the RM and WSJ corpora show that while a classical semi-continous
can still yield competitive results while using fewer Gaussian components. system does not perform as well as a continuous one, multiple-codebook semi-continuous
Our best semi-continous systems included full-covariance codebook Gaussians, systems can perform better, particular when using full-covariance Gaussians.
multiple codebooks, and smoothing of the weight parameters.
\end{abstract} \end{abstract}
\begin{keywords} \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