mirror of
https://github.com/MartinThoma/LaTeX-examples.git
synced 2025-04-28 23:37:57 +02:00
32 lines
1.3 KiB
TeX
32 lines
1.3 KiB
TeX
|
\subsection{What will I do next?}
|
||
|
|
\begin{frame}{What will I do next?}
|
||
|
|
\begin{itemize}
|
||
|
|
\item Get classification performance with cross-validation
|
||
|
|
\item Implement neural net for classification
|
||
|
|
\begin{itemize}
|
||
|
|
\item preprocessing: compute cubic spline for each line
|
||
|
|
\begin{itemize}
|
||
|
|
\item equi-spaced points or
|
||
|
|
\item get equi-timed points
|
||
|
|
\end{itemize}
|
||
|
|
\item 5 - 20 input neurons for each line
|
||
|
|
\item 1076 output neurons (one for each symbol)
|
||
|
|
\end{itemize}
|
||
|
|
\item Get a language model (e.g. by parsing Wikipedia)
|
||
|
|
\item Use ANN with HMM (?)
|
||
|
|
\end{itemize}
|
||
|
|
\end{frame}
|
||
|
|
|
||
|
|
\subsection{Far future}
|
||
|
|
\begin{frame}{What could be done?}
|
||
|
|
\begin{itemize}
|
||
|
|
\item Make use of audio data in a multimodal approach\\
|
||
|
|
e.g. $R$ and $\mathcal{R}$
|
||
|
|
\item Currently, the Lecture Translation system doesn't recognize math.\\
|
||
|
|
You get \enquote{integral of e raised to the power of x d x} instead
|
||
|
|
of $\int e^x \mathrm{d} x$.
|
||
|
|
\item Spoken math is ambigous: $\sqrt{a+b}$ vs. $\sqrt{a} + b$
|
||
|
|
\item The language model I create could help to find probable formulas
|
||
|
|
\item The platform could be used to get more input data of users
|
||
|
|
\end{itemize}
|
||
|
|
\end{frame}
|