We present PiPo, a plugin API for data stream processing with applications in interactive audio processing and music information retrieval as well as potentially other domains of signal processing. The development of the API has been motivated by our recurrent need to use a set of signal processing modules that extract low-level descriptors from au...
Second screen applications are becoming key for broadcasters exploiting the convergence of TV and Internet. Authoring such applications however remains costly. In this paper, we present a second screen authoring application that leverages multimedia content analytics and social media monitoring. A back-office is dedicated to easy and fast content i...
The collaborative research and development project DYCI2, Creative Dynamics of Improvised Interaction, focuses on conceiving, adapting, and bringing into play efficient models of artificial listening, learning, interaction, and generation of musical contents. It aims at developing creative and autonomous digital musical agents able to take part in ...
Interactive multimedia system usually represents computations as a dataflow graph – the patching model. Nowadays , dataflow graphs integrate multiple medias from various dedicated languages and systems, with multiple rates, for instance audio rate, video rate, control rate, but also the rate of FFT frames, as well as requirements on buffer sizes, o...
This paper presents the model of time developed in the ver- sion 1.0 of the Antescofo system. Antescofo integrates a listening module with a dedicated reactive and timed real- time programming language used to define the electronic actions to be performed in sync with a human performer. Since its beginnings, the model of time supported by the DSL h...
Numeric musical and artistic creation is in great part based on well-known patcher softwares: Max, PureData, Open-Music, vvvv… Yet, handling temporal evolutions and structures on large scales remains a central problem: for instance, writing a song with introduction, chorus, verse, chorus, parts in Max presents many hurdles to the composer. Hence, m...
The traditional role of nearest-neighbor classification in musicclassification research is that of a straw man opponent for the learningapproach of the hour. Recent work in high-dimensional indexinghas shown that approximate nearest-neighbor algorithms are extremelyscalable, yielding results of reasonable quality from billions of high-dimensionalfe...
There has been a significant interest in providing immersive listening experiences for a variety of applications, and recent improvements in audio production have provided the capability for 3D audio practitioners to produce realistic and imaginative immersive auditory scenes. Even though technologies to reproduce 3D audio content are becoming read...
Visual biofeedback is the process of gaining awareness of physiological functions through the display of visual information. As speech is concerned, visual biofeedback usually consists in showing a speaker his/her own articulatory movements, which has proven useful in applications such as speech therapy or second language learning. This article pre...
In this paper we propose a real-time selective video encryption solution in the scalable extension of High Effciency Video Coding(HEVC) standard, referred to as SHVC. The proposed scheme encrypts a set of sensitive SHVC parameters with a minimum delayand complexity overheads. The encryption process is performed at the CABAC binstring level and fulf...
