On the Freesound site we have reached another important milestone. There are now 50000 sounds contributed by the community.
News and Events
|
Freesound has reached 50000 sounds
|
|
Xavier Serra da una conferencia en el Planetario de Pamplona
El 20 de Mayo y dentro del ciclo de conferencias "ARTE, CIENCIA Y TECNOLOGÍA: miradas diferentes a una misma realidad" organizado por la |
|
Reactable wins two yellow pencil awards
The Reactable team has won two D&AD yellow pencil awards in this years competition. Martin Kaltenbrunner received the awards on behalf of the team during the awards ceremony that took place on May 15th at the South Bank's Royal Festival Hall in London. One of the awards was in the category of Digital Installations and the other in the category of Environmental Design. The D&AD Awards, familiarly known as the ‘Yellow Pencils’, are the most internationally respected and prestigious creative awards for the design and advertising industries. |
|
Seminar by Jordi Janer on voice-driven applications
Jordi Janer will give a seminar entitled "Voice-driven applications
based on Hidden Markov Models" on Thursday 15th of May at 3pm in room
102 of the França building.
Abstract: The voice is our primary mean of communication. However, the use of the voice in human-computer interaction is, still nowadays, limited to very specific situations. Nevertheless, past research in Speech Processing has brought a number of techniques that can be applied to voice interactive systems, e.g. Hidden Markov Models. Hidden Markow Models (HMM) is a well known statistical technique for temporal pattern recognition that has been widely used in Automatic Speech Recognition (ASR). In this presentation, we review first the main concepts of HMM's. Next, we present two common voice applications based HMM: keyword spotting and phonetic alignment. The former is integrated in a language education software for children, while the latter is the front-end of a real-time voice-driven singing voice synthesizer. |
|
Perfecto Herrera gives a tutorial at the AES convention
Perfecto Herrera will give a tutorial on "Intelligent Audio Systems: A
Review of the Foundations and Applications of Semantic Audio Analysis
and Music Information Retrieval" at the AES convention that will take
place in Amsterdam from the 17th to the 20th of May.
Abstract: This tutorial will target students, researchers, and industry audio engineers who are unfamiliar with the field of Music Information Retrieval (MIR). We will demonstrate the myriad of exciting technologies enabled by the fusion of basic signal processing techniques with machine learning. The presentation will be a high-level, applied, multimedia-rich, overview of the building blocks of MIR systems. Our goal is to make highly-interdisciplinary technologies and dauntingly-complex algorithms approachable. In the spirit of modern cooking shows, we will perform numerous demonstrations, including on-the-fly coding of basic "intelligent audio" systems, prepared system demonstrations, and prepared audio examples demonstrating more complex systems. |
|
Seminar by Olivier Lartillot on his MIRtoolbox
Olivier Lartillot, from the Finnish Center of Excellence in
Interdisciplinary Music Research, on Thursday 8th of May at 3pm in room
102 of the França building, will give a seminar entitled "MIRtoolbox, a
Matlab toolbox for musical feature extraction from audio."
Abstract: In the context of a European project called "Brain Tuning" -- and dedicated to the study of the interrelations between music ans emotion --, we are developing MIRtoolbox, a Matlab toolbox for musical feature extraction from audio. This seminar will present an overview of the toolbox, showing the set of operators and features that can be extracted from audio files. The toolbox can be controlled using a user-friendly syntax allowing the design of elaborate processes without having to care about technical details. Memory management and batch processing mechanisms operating in the background allow an extensive application of the toolbox to large-scale analyses. Improvements offered by the update 1.1, just released, will be mentioned as well. Finally, some applications of the toolbox to the study of the interrelationships between musical features and induced emotions will be shown. |
|
Call for participation for DAFxTRa 2008
DAFxTRa 2008 (DAFx Transformation RAting) is a new initiative promoted by the MTG aimed at evaluating and comparing algorithms for audio effects. Our goal is to have the main evaluation in September 2008 during DAFx-08 (http://www.acoustics.hut.fi/dafx08/) but to make it happen we need the involvement of the audio effects research community. |
|
Ponències al 2n Congrés Internacional de Música a Catalunya
Perfecto Herrera, Alex Loscos i Xavier Serra seran ponents en el 2n Congrés Internacional de Música a Catalunya que se celebrarà a la seu central de la Universitat de Barcelona els dies 8, 9 i 10 de Maig del 2008. Perfecto Herrera, investigador del MTG, però també Cap del Departament de Sonologia de l’Escola Superior de Música de Catalunya (ESMUC) parlarà sobre "Investigació i educació en tecnología musical a Catalunya", dins l'àmbit d'Educació Musical. Àlex Loscos, CEO de BMAT, parlarà sobre "La creació de perfils musicals d’usuari", dins l'àmbit de Indústria i mitjans de comunicació. Xavier Serra, director del MTG, parlarà sobre "De la cultura musical a la cultura del so en la societat tecnològica", dins l'àmbit de Usos socials de la música. |
|
HCI research agenda promoted by Microsoft
Sergi Jordà was one of the "luminaries" that participated in the forum entitled "HCI 2020: Human Values in a Digital Age" sponsored by Microsoft Research that has produced the report called "Being Human: Human-Computer Interaction in the Year 2020". This report aims at formulating an agenda for human-computer interaction (HCI) over the next decade and beyond. |
|
Presence of MTG people at various events
Emilia Gómez will talk about "Análisis tonal automático de grabaciones musicales" and Jordi Bonada will talk about "Análisis, procesado y sintesis de voz cantada", both at the "II Seminario de Ciencia Computational y Música Flamenca" that will take place on April 2nd and 3th of 2008 in Sevilla. Joan Serrà will present the paper "Audio Cover Song Identification based on Tonal Sequence Alignment", written together with Emilia Gómez, at the IEEE-ICASSP conference in Las Vegas on April 3rd ( http://www.icassp2008.com). Òscar Celma will give a talk on "Pharos Project: Using AV-RSS for Publishing Audiovisual Content Metadata" at the workshop "The Future of Web Search: Beyond Text" that will take place on April 4th and 5th in Andorra ( http://grupoweb.upf.es/tfws08/). Sergi Jordà and Martin Kaltenbrunner will play the Reactable on a concert with the thereminist Dorit Chrysler in the Auditori of Barcelona on Sunday 6th (Concert info) Xavier Serra will give a guest lecture on April 9th at the Media Technology Days organized by the University of Linkoping in Sweden ( http://www.mtd.medieteknik.nu) Bram de Jong will talk about Freesound at the "Jornadas del Conocimiento Libre" organized by the Universidad Europea de Madrid in Madrid on April 15th and 16th. |
