Updated submission deadline: 5 February, 2015.
THEME AND SCOPENeural Networks (NN) based techniques, and Computational Intelligence (CI) ones from a wider perspective, are largely used to face complex modelling, prediction, and recognition tasks in different research fields. One of these is represented by Digital Audio, which finds application in contexts like entertainment, security, and health. Scientists and technicians worldwide actively cooperate to develop new services and products, and they typically employ advanced NN and CI techniques, in combination with suitable Digital Signal Processing algorithms.
In particular, this is typically accomplished with the aim of extracting and manipulating useful information from the audio stream to pilot the execution of automatized services, also in an interactive fashion. Several are the Digital Audio topics touched by such a paradigm, involving different kinds of audible signals. In the “music” case study we have the music information retrieval with many diverse sub-topics therein; for “speech” we can mention speech/speaker recognition, speaker diarization, speaker localization; in the case of “sound”, acoustic monitoring and sound detection and identification have lately registered a big interest among the scientists working in the field. Moreover, also cross-domain approaches to exploit the information contained in diverse signals in the acoustic range have been also recently developed. In many applicative contexts, this happens in conjunction with data coming from other media, like textual and visual, for which specific fusion techniques are required.
In dealing with the problems correlated to these topics, the adoption of data-driven learning systems is often a ``must'', and the recent success encountered by deep neural architectures comes just in confirmation of that. This is not, however, immune to technological issues, due to the presence of non-stationary operating conditions and hard real-time constraints (made often harder by the big amount of data to process).
It is indeed of great interest for the scientific community to understand how and to what extent novel CI based techniques (with special attention to the NN ones) can be efficiently employed in Digital Audio, in the light of all aforementioned aspects. The aim of the session is therefore to focus on the most recent advancements in the CI field and on their applicability to Digital Audio problems.
TOPICSPotential topics include, but are not limited to:
- Computational Audio Analysis
- Deep Learning algorithms in Digital Audio
- Neural Architectures for Audio Processing
- Music Information Retrieval
- Speech/Speaker Analysis and Classification
- Sound Detection and Identification
- Acoustic Source Separation
- Brain inspired auditory scene analysis
- Cross-domain Audio Analysis
- Speech and Audio Forensics
- Audio-based Security Systems
- Intelligent Audio Interfaces
- UPDATED February 5, 2015: Paper submission deadline
- March 15, 2015: Notification of paper acceptance
- April 15, 2015: Camera-ready deadline
- July 11-16, 2015: Conference days
ORGANIZERSStefano Squartini, Università Politecnica delle Marche, Italy, email@example.com
Aurelio Uncini, Università La Sapienza, Italy, firstname.lastname@example.org
Björn Schuller, University of Passau, Germany/Imperial College London, UK, email@example.com
Francesco Piazza, Università Politecnica delle Marche, Italy, firstname.lastname@example.org