17 research outputs found
On-edge adaptive acoustic models: an application to acoustic person presence detection
No full textstatus: Publishe
The Impact of Missing Labels and Overlapping Sound Events on Multi-label Multi-instance Learning for Sound Event Classification
No full textAutomated analysis of complex scenes of everyday sounds might help us navigate within the enormous amount of data and help us make better decisions based on the sounds around us. For this purpose classification models are required that translate raw audio to meaningful event labels. The specific task that this paper targets is that of learning sound event classifier models by a set of example sound segments that contain multiple potentially overlapping sound events and that are labeled with multiple weak sound event class names. This involves a combination of both multi-label and multi-instance learning. This paper investigates two state-of-theart methodologies that allow this type of learning, LRM-NMD and CNN. Besides comparing the accuracy in terms of correct sound event classifications, also the robustness to missing labels and to overlap of the sound events in the sound segments is evaluated. For small training set sizes LRM-NMD clearly outperforms CNN with an accuracy that is 40 to 50% higher. LRM-NMD does only minorly suffer from overlapping sound events during training while CNN suffers a substantial drop in classification accuracy, in the order of 10 to 20%, when sound events have a 100% overlap. Both methods show good robustness to missing labels. No matter how many labels are missing in a single segment (that contains multiple sound events) CNN converges to 97% accuracy when enough training data is available. LRM-NMD on the other hand shows a slight performance drop when the amount of missing labels increases.15916
THE IMPACT OF MISSING LABELS AND OVERLAPPING SOUND EVENTS ON MULTI-LABEL MULTI-INSTANCE LEARNING FOR SOUND EVENT CLASSIFICATION
No full textstatus: Published onlin
Acoustic Event Classification using Low-Resolution Multi-label Non-negative Matrix Deconvolution
No full textAcoustic Event Classification Using Low-Resolution Multi-Label Non-Negative Matrix Deconvolution
No full textAcoustic event classification for monitoring applications is becoming feasible thanks to the increasing number of connected devices with a built-in microphone. The sound event classes are defined by annotating training data, which is a laborious process. Attempts have been made to reduce the workload on annotating the vast amounts of training data and are referred to as semi-supervised learning and active learning. In this paper we propose a non-negative matrix deconvolution (NMD) based approach, capable of modeling acoustic events from data labeled on a low-resolution and multi-label level and thereby reducing the annotation workload. We further show that the proposed extension of NMD is successfully applied for the classification of acoustic events, even in noisy conditions and with overlapping events.sponsorship: This work was performed in the context of following projects: VLAIO doctoral scholarship (contract 121565) and Sound INterfacing through the Swarm - SINS (VLAIO-SBO contract 130006). (VLAIO doctoral scholarship|121565, Sound INterfacing through the Swarm - SINS (VLAIO-SBO)|130006)status: Publishe
AUTOMATIC MONITORING OF ACTIVITIES OF DAILY LIVING USING A WIRELESS ACOUSTIC SENSOR NETWORK
No full textstatus: Publishe
An exemplar-based NMF approach to audio event detection
No full textWe present a novel, exemplar-based method for audio event detection based on non-negative matrix factorisation. Building on recent work in noise robust automatic speech recognition, we model events as a linear combination of dictionary atoms, and mixtures as a linear combination of overlapping events. The weights of activated atoms in an observation serve directly as evidence for the underlying event classes. The atoms in the dictionary span multiple frames and are created by extracting all possible fixed-length exemplars from the training data. To combat data scarcity of small training datasets, we propose to artificially augment the amount of training data by linear time warping in the feature domain at multiple rates. The method is evaluated on the Office Live and Office Synthetic datasets released by the AASP Challenge on Detection and Classification of Acoustic Scenes and Events. © 2013 IEEE.status: Publishe
Monitoring Activities of Daily Living Using Wireless Acoustic Sensor Networks in Clean and Noisy Conditions
No full textThis work examines the use of a Wireless Acoustic Sensor Network (WASN) for the classification of clinically relevant activities of daily living (ADL) of elderly people. The aim of this research is to automatically compile a summary report about the performed ADLs which can be easily interpreted by caregivers. In this work, the classification performance of the WASN will be evaluated in both clean and noisy conditions. Results indicate that the classification performance of the WASN is 75.3±4.3% on clean acoustic data selected from the node receiving with the highest SNR. By incorporating spatial information extracted by the WASN, the classification accuracy further increases to 78.6±1.4%. In addition, the classification performance of the WASN in noisy conditions is in absolute average 8.1% to 9.0% more accurate compared to highest obtained single microphone results.sponsorship: This work was performed in the context of following projects: IWT doctoral scholarships (contract 111433 and 121565), Sound INterfacing through the Swarm – SINS (IWT-SBO contract 130006), Algorithms, Architectures and Platforms for Enhanced Living Environments – AAPELE (FP7-COST Action IC1303) and Profound (EC-ICT-PSP contract 325087).status: Publishe
Footstep localization based on in-home microphone-array signals
No full textThis paper describes a system able to detect footstep locations. Through acoustic information retrieved from a wireless sensor network with small and relatively cheap microphone arrays. A dataset was recorded in order to validate the accuracy of the detection. Results on this dataset show that a best median of errors of 31cm per time moment are achievable, but results heavily depend on the positions of the microphones relative to the footsteps.status: Publishe
