Blog

-- Thoughts on data analysis, software development and innovation management. Comments are welcome

EmoLib demo - Now available

08-Jul-2010

EmoLib is shown to the world in the form of a web service with servlet technology, available here. Its performance features will (hopefully) be enhanced as my research advances.

Enjoy ;)

Dissertation on sentiment analysis - Now available

01-Jul-2010

I've just made available the supervised work of my dissertation on sentiment analysis under a Creative Commons license (by-nc-sa) (see my Publications section). I've left out the doctorate courses I attended and some padding "fashion" stuff. Nevertheless, the whole dissertation is available at the library of the university or on (polite) demand :)

I must say, though, that some numbers vary slightly as my interpretation of the Inverse Term Frequency for weighting text in the Associative Relational Network is different from [Alias et al., 2008]. Anyhow, the overall results and conclusions remain the same despite this silly misunderstanding. In case of any doubt, please don't hesitate to contact me. I'll be glad to know of your interest in my research.

Dissertation on sentiment analysis

09-Jun-2010

Yesterday I defended my dissertation on sentiment analysis, actually entitled "Natural Language Processing techniques applied to speech technologies". The gist of this research is the automatic extraction of affective information from text in order to feed a speech enabled application with this particular human feature. For example, in a speech synthesis environment, the system would be directed by these affective tags in order to yield expressiveness in speech. Conversely, in a speech recognition environment, the system would enable dealing with the textual domain and refine its recognition capabilities. In all, this value-add should help improve the interface between humans and machines.

I'm very content because I got very interesting feedback from the examining board (and also because they gave it an excellent mark ;) I'm looking forward to publishing the results as soon as possible. Thanks to all who supported and advised me during these two years. Indeed.

Robots taking control of La Salle

23-Apr-2010

First of all, let me wish all the Georges have a nice day. Then, I just wanted to mention the robotic platform that La Salle presented yesterday as a complementary part of the Engineering (and Business) courses, the LS Maker (that is not this Light Saber Maker), see this video and this article. My devotion to robots was already shown in an older post. As one of its marketing features, students are enticed to implement a voice recognition system on it! That's awesome! I wish I had had one of these during my undergraduate years!

Swift GNU/Linux tools stay alive

19-Apr-2010

Have a butcher's hook (Cockney English for "look") at this Linux Journal article about my favourite GNU/Linux distro setup: Debian with a most lightweight configuration. I have used it for the past four years, after trying several fashionable distros, and I definitely keep it for the same reasons stated in the article. Nevertheless, to my taste, XFCE has become too complex (and heavy) for me and my PC, and I still rather prefer using Blackbox with bbkeys for keyboard shortcuts. That is really fast on a modest computer!

Moving from Alpine to Roundcube webmail

15-Apr-2010

If you are (like me) still stubborn using text-based interfaces and you feel pushed to using "newer" technologies, this post may be of your interest.

A while ago the IT department of the university announced they would be ceasing support to Alpine, one of the most beloved e-mail clients, see Linus' choice at this Lifehacker interview. I was taught this fabulous application when I first came to university, and now I am forced to no longer use it. Instead, Roundcube is the candidate to replace it. Actually, Roundcube is more beautiful, it uses drag-and-drop, etc... a piece of software for the masses, but it still misses the enchanting interface of the console.

If anyone goes through the same situation, I have coded a helpful Perl snippet, available here, that takes Alpine's addressbook file and transforms it into a vCard format, ready to be loaded into Roundcube. I hope this is of help to make the transition process a little bit lighter :)

Automating game development with text-based technologies

15-Apr-2010

Since my last post was dedicated to relating speech technologies with game development, and yesterday I came across a similar issue but with text technologies in a Linked-in discussion, the so-called Text-to-Scene conversion, I thought it also deserved a blog entry.

The gist of it is the generation of a 3D scene according to a textual description of that scene, as natural language is supported to be an easy and effective medium for describing visual ideas and mental images. See this paper written by Bob Coyne and Richard Sproat for further details. Definitely, IMO it's fascinating, despite being a technology that is 9 years old. With a beautiful TTS system, would you imagine synthesising (scene + spoken dialogs) those "Choose Your Own Adventure" books following a copy-and-paste procedure?

Speech technologies growing among open source game development

04-Nov-2009

Speech technologies are on the rise among open source game development communities. For example, check the announcement of the BennuGD WIZ/PC contest. This suite recently enables the incorporation of a speech synthesis engine, see this, in order to permit the interaction of speaking avatars. Game technologies grow mature in time, they need to provide more demanding features and speech technologies seem to be one the most challenging engineering sciences to supply this requirements. Will emotion analysis ever fit in this field? Very likely.

Emotion detection using both acoustic and linguistic information in children's speech

27-Oct-2009

Dr. Michael Wagner, director of the National Center for Biometric Studies at the University of Canberra, Australia, has given a speech on emotion analysis at UPC. He has presented their contribution to the Emotion Challenge that was held last September at Interspeech. They proposed the fusion of acoustic and linguistic features in order to detect emotion states in children's speech.

He has proposed the acquisition of a host of acoustic features to get the most out of the plain speech signal, an approach he himself has criticized for being unscientific. With respect to the linguistic characterization of speech they detected a list of emotionally salient words and compared its decision with the one provided by the acoustic module. Although his publication did not win the challenge, their approach is very interesting and innovative since they were the only participating team that considered linguistic features.

Text Analysis in Writing Research

19-Oct-2009

Today Dr. Nancy Nelson, from the University of North Texas, has given a speech on Text Analysis in Writing Research at Blanquerna. She has tackled the problem very philosophically, aside from the engineer's eye view of text mining, with an insight into the cultural and historical situations and how these factors influence orientation towards writing. Very interesting.

All contents © Alexandre Trilla 2008-2025