From: Thomas Fillon Date: Fri, 12 Sep 2014 00:41:11 +0000 (+0200) Subject: Update DLFM 2014 slides X-Git-Url: https://git.parisson.com/?a=commitdiff_plain;h=e501094f6957bf495c1c41e54491dc70014739dc;p=telemeta-doc.git Update DLFM 2014 slides --- diff --git a/Conferences/2014_DLFM/slides/slides_DLFM2014.tex b/Conferences/2014_DLFM/slides/slides_DLFM2014.tex index 956476c..c748714 100644 --- a/Conferences/2014_DLFM/slides/slides_DLFM2014.tex +++ b/Conferences/2014_DLFM/slides/slides_DLFM2014.tex @@ -129,7 +129,7 @@ \begin{itemize} \item Since 2007, the Research Center for Ethnomusicology (CREM) and Parisson have been developing an innovative, collaborative and - open-source web-based multimedia platform for humanities and social sciences research. + open-source \alert{web-based multimedia platform} for \alert{humanities and social sciences research}. % \item Main goals: % \begin{itemize}\scriptsize % \setbeamertemplate{itemize subitem}[triangle] @@ -144,8 +144,8 @@ \emph{Sound archives of the CNRS - Musée de l'Homme} \colorbox{yellow!40} {\bf \url{http://archives.crem-cnrs.fr}} \end{center} - \item This collaborative platform support numerous aspects of the field of - ethnomusicology, ranging from musical analysis to comparative + \item This \alert{collaborative} platform support numerous aspects of the field of + \alert{ethnomusicology}, ranging from musical analysis to comparative history and the anthropology of music. The platform also provides a useful resources for the fields of anthropology, linguistics and acoustics. @@ -157,7 +157,7 @@ \begin{block}{Towards automatic audio content analysis ...} \begin{itemize} - \item Recently, an open-source audio analysis framework, + \item Recently, an open-source \alert{audio analysis framework}, TimeSide, has been developed to bring automatic audio content analysis capabilities to the Telemeta web platform. \end{itemize} @@ -189,8 +189,8 @@ \end{block} \begin{block}{An open-source software} \begin{itemize} - \item Telemeta, is a free and open source (\emph{GPL-like}) - software in accordance with open web standards. + \item Telemeta, is a free and open source software (\emph{GPL-like} licence) + in accordance with open web standards. \end{itemize} \vspace{-0.5cm} \begin{center} @@ -216,13 +216,10 @@ \item Database management through Strong Structured Query Language (\alert{SQL}) or Oracle backend. \item \alert{On-the-fly audio analyzing}, transcoding and metadata embedding in various multimedia formats, provided through an external component, \emph{TimeSide}. - \item Social editing with semantic ontologies, smart workflows, - realtime tools, human or automatic annotations and - segmentations. + \item Social editing with semantic ontologies, smart workflows, human or automatic annotations and segmentations. \item \alert{User management} with individual desk, playlists, profiles and group access rights. \item High level \alert{search engine} \hyperlink{geonavigator}{geolocation}, instruments, ethnic groups, etc...). - \item Data providers : DublinCore, OAI-PMH, RSS, XML, JSON and other. \item \hyperlink{telemeta_languages}{Multi-language support (currently english, german, french and chinese).} \end{itemize} \end{block} @@ -233,7 +230,7 @@ \begin{frame}\frametitle{Metadata} \begin{block}{} In addition to the audio data, an efficient and dynamic management - of the associated metadata is also necessary. + of the associated metadata is also offered. \begin{itemize} \item Metadata provides valuable information about the \alert{source of the data} and to the related \alert{work of @@ -339,27 +336,23 @@ \end{frame} -\begin{frame}{Descriptive and analytical information on the audio content}{Annotations}\scriptsize +\begin{frame}{Descriptive and analytical information on the audio content}{Annotations}%\scriptsize \begin{columns}[T] \begin{column}{0.6\textwidth} \begin{block}{Markers}%\tiny \begin{itemize} \item The embedded audio player also enables annotation of the - audio content through time-coded markers. - \item These annotations are accessible from the sound archive - item web page and are indexed through the database. + audio content through \alert{time-coded markers}. + \item These annotations are \alert{indexed through the database}. -\item Such annotations consist of a title and a free text - field associated with a given time position. + \item Users can create their own annotations and \alert{share} them with colleagues. - \item Ethnomusicologists, archivists, anthropologists, - linguists and acousticians working on sound documents can - create their own annotations and share them with colleagues. - - %\item \emph{The possibility for experts to annotate time-segments - % over a zoomable representation of the sound is currently - % under development in order to improve the accuracy and the - % quality of time-segment-based annotations.} + % \item \emph{The possibility for experts to annotate + % time-segments + % over a zoomable representation of the sound is currently + % under development in order to improve the accuracy and + % the + % quality of time-segment-based annotations.} \end{itemize} \end{block} @@ -380,7 +373,7 @@ rely on an external component, \emph{TimeSide}. \item TimeSide is an \emph{open-source} \alert{audio analysis and visualization framework} based on - both Python and JavaScript languages that provides + both \alert{Python and JavaScript} languages that provides state-of-the-art signal processing and machine learning algorithms together with \alert{web audio} capabilities for displaying and streaming files. @@ -392,9 +385,7 @@ \begin{block}{Audio management} TimeSide provides the following main features: \begin{itemize} - \item Secure archiving, editing and publishing of audio files over - the internet. - \item Smart dynamic audio player with enhanced visualization (e.g. waveform, + \item Smart dynamic audio player with enhanced visualization (e.g. waveform, spectrogram) that can be embedded into any html page through \emph{iframe} (live example: \href{http://yomix.org/category/projects.html}{Yomguy blog}) \item Multi-format support: decodes the vast majority of audio and video formats% through Gstreamer and transcodes them with smart @@ -412,7 +403,7 @@ \subsection{Audio features extraction} \begin{frame}{Audio features extraction} \begin{block}{Audio features extraction} -TimeSide incorporates some state-of-the-art audio feature extraction libraries such as: +TimeSide incorporates some state-of-the-art \alert{audio feature extraction libraries} such as: \vspace{-0.1cm} \begin{itemize} \item Aubio: @@ -429,13 +420,14 @@ Given the extracted features, every sound item in a given collection can be automatically analyzed.\\ The results of this analysis can be: - \begin{itemize}\scriptsize + \begin{itemize}\footnotesize + \item Serialized to the web browser through common markup languages: + XML, JSON and YAML \item Stored in a scientific file format (e.g. NumPy format or HDF5) \item Exported to sound visualization and annotation software (e.g. Sonic Visualizer) - \item Serialized to the web browser through common markup languages: - XML, JSON and YAML + \end{itemize} \end{block} @@ -454,17 +446,13 @@ The results of this \begin{block}{} \begin{itemize} \item Since June 2011, the Telemeta platform has been used by - the Sound archives of the CNRS - Musée de - l'Homme\footnote{\url{http://archives.crem-cnrs.fr}} and + the \alert{Sound archives of the CNRS - Musée de + l'Homme}\footnote{\url{http://archives.crem-cnrs.fr}} and managed by the CREM. - \item According to the CREM specific aims, the Telemeta - platform makes these archives available for researchers, + \item These archives available for researchers, students and (when copyright allows) to a broader audience. - \item The Sound archives of the \emph{CNRS - Musée de l'Homme} is one of - the most important in Europe and contains commercial and - unpublished recordings of music and oral traditions from around - the world -\item Through this platform, these archives can be shared, + \item It is one of the most important Sound archives librairy in Europe + \item Through this platform, these archives can be shared, discussed and analyzed. @@ -480,9 +468,9 @@ The results of this \begin{itemize} \item The Sound archives of the \emph{CNRS - Musée de l'Homme} have been collected by researchers attached to numerous research - institutions across the world, including prominent figures of - the field of ethnomusicology (among which Brailoiu, Lomax, - Shaeffner, Rouget and Elkin). + institutions across the world. %, including prominent figures of + %the field of ethnomusicology (among which Brailoiu, Lomax, + %Shaeffner, Rouget and Elkin). \item Most of the recordings come from the fieldwork of researchers in \alert{all continents} during the last \alert{110 years}. @@ -548,11 +536,11 @@ The results of this \section[The DIADEMS project]{The DIADEMS project}\label{sec:Diadems} \subsection{Consortium and goals} \begin{frame}{The DIADEMS project} - \tiny + \scriptsize Started in January 2013, the French national research program DIADEMS is a multi-disciplinary project dedicated to the \alert{Description, Indexation, Access to Ethnomusicological and Sound Documents}. - \begin{block}{The consortium} + \begin{block}{The consortium}\tiny \begin{columns}[T] \begin{column}{.5\textwidth} \begin{block}{Science and Technology of Information and @@ -597,15 +585,12 @@ The results of this \begin{block}{Goals and on-going development} \begin{itemize} \item The goal of the DIADEMS project is to develop computer tools - to \emph{automatically} index the recording content directly - from the audio signal. + to \alert{automatically index} or assist the indexation of the recording content from the audio signal. \item Ongoing work consists of implementing - advanced classification, indexation, segmentation and similarity - analysis methods. - \item Besides music analysis, such automatic tools also deal with speech - and other types of sounds classification and segmentation to - enable a more exhaustive annotation of the audio materials. - \item Ethnomusicological recordings contain not only music but also speech, environmental noises and noises generated by the recording process that could also be indexed. + advanced \alert{classification, indexation, segmentation and similarity + analysis} methods. + \item \alert{Besides music analysis}, such automatic tools also deal with speech + and other types of sounds present ethnomusiclogical recordings like \alert{speech, environmental noises and noises generated by the recording process} \end{itemize} @@ -616,13 +601,13 @@ The results of this \begin{frame}{The method of a new interdisciplinary research} \begin{block}{} \begin{itemize} - \item In this research program, groups from different backgrounds + \item In this research program, groups from \alert{different backgrounds} are working together. \item The first challenge was to initiate a common interest and a - mutual understanding. + \alert{mutual understanding}. \item In this process, DIADEMS gave us the opportunity to improve - our understanding on the link between the semantics and - acoustics of voice production. + our understanding on the \alert{link between the semantics and + acoustics of voice production} in order to be able to specify the classification and indexation tasks. \end{itemize} \end{block} % In preliminary work, we attempted to first define vocal @@ -659,28 +644,27 @@ The results of this \end{frame} -\subsection{Automatic tools for assisting indexation and annotation of audio documents} -\begin{frame}{Automatic tools for assisting indexation and annotation of audio documents} - \begin{block}{On-going development} - \begin{itemize} - \item Analysis of recording sessions - \item Analysis of speech and singing voice segments through speech - activity detection - \item Analysis of music segments - \begin{itemize} - \item Music / Speech segmentation - \item Monophony / Polyphony segmentation - \item Automatic instrument classification - \end{itemize} - \end{itemize} - \end{block} - -\end{frame} +% \subsection{Automatic tools for assisting indexation and annotation of audio documents} +% \begin{frame}{Automatic tools for assisting indexation and annotation of audio documents} +% \begin{block}{On-going developments} +% \begin{itemize} +% \item Analysis of recording sessions +% \item Analysis of speech and singing voice segments through speech +% activity detection +% \item Analysis of music segments +% \begin{itemize} +% \item Music / Speech segmentation +% \item Monophony / Polyphony segmentation +% \item Automatic instrument classification +% \end{itemize} +% \end{itemize} +% \end{block} +%\end{frame} \subsection{Evaluation and future improvements} \begin{frame}{Evaluation and Future improvements} \begin{block}{Development and Evaluations} \begin{itemize} - \item At the end of the first step of the project, interesting + \item Interesting preliminary results have been obtained regarding the detection of start times of recording sessions, speech recognition, singing voice recognition and musical instrument family @@ -689,8 +673,7 @@ The results of this \item The robustness of these processings is assessed using \alert{criteria defined by the final users}: teachers, students, researchers and musicians. - \item After validation, Analysis and Annotation tools, as well as the provided - annotations, will be integrated in the Telemeta platform. + \item \alert{After validation}, Analysis and Annotation tools, as well as the provided annotations, will be integrated in the Telemeta platform. \end{itemize} \end{block}