Automatic discrimination of musical signal types as speech, singing, music, genres or drumbeats within audio streams is of great importance e.g. for radio broadcast stream segmentation. Yet, feature sets are largely discussed. We therefore suggest a large open feature set approach starting with systematical generation of 7k hi-level features based on MPEG-7 Low-Level-Descriptors and further feature contours. A subsequent fast Gain Ratio reduction followed by wrapper-based Floating Search leads to a strong basis of relevant features. Next, features are added by alteration and combination within genetic search. For classification we use Support-Vector-Machines proven reliable for this task. Test-runs are carried out on two task-specific databases and the public Columbia SMD database and show significant improvements for each step of the suggested novel concept.
The multi-modal multi-sensor PROMETHEUS database was created in support of research and development activities [PROMETHEUS (FP7-ICT-214901): http://www.prometheus-FP7.eu] aiming at the creation of a framework for monitoring and interpretation of human behaviors in unrestricted indoor and outdoor environments. The distinctiveness of the PROMETHEUS database comes from the unique sensor sets, used in the various recording scenarios, but also from the database design, which covers a range of real-world applications, correlated to smart-home automation and indoors/outdoors surveillance of public areas. Numerous single-person and multi-person scenarios, but also scenarios with interactions between groups of people, motivated by these applications were implemented with the help of skilled actors and supernumerary personnel. In these scenarios, the actors and personnel were instructed to implement a range of typical and atypical behaviors, and simulations of emergency and crisis situations. In summary, the database contains more than 4 h of synchronized recordings from heterogeneous sensors (an infrared motion detection sensor, thermal imaging cameras, overview/surveillance video cameras, close-view video cameras, a 3D camera, a stereoscopic camera, a general-purpose camcoder, microphone arrays, and motion capture equipment) collected in common setups, simulating smart-home environment, airport, and ATM security environment. Selected scenes of the database were annotated for the needs of human detection and tracking. The entire audio part of the database was annotated for the needs of sound event detection, sound source enumeration, emotion recognition, etc
Recognition of emotion in speech usually uses acoustic models that ignore the spoken content. Likewise one general model per emotion is trained independent of the phonetic structure. Given sufficient data, this approach seemingly works well enough. Yet, this paper tries to answer the question whether acoustic emotion recognition strongly depends on phonetic content, and if models tailored for the spoken unit can lead to higher accuracies. We therefore investigate phoneme-, and word-models by use of a large prosodic, spectral, and voice quality feature space and Support Vector Machines (SVM). Experiments also take the necessity of ASR into account to select appropriate unitmodels. Test-runs on the well-known EMO-DB database facing speaker-independence demonstrate superiority of word emotion models over todays common general models provided sufficient occurrences in the training corpus.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.