Acoustic Monitoring and Localization for Social Care

Goetze, Stefan; Schröder, Jens; Gerlach, Stephan; Hollosi, Danilo; Appell, Jens-E.; Wallhoff, Frank

doi:10.5626/jcse.2012.6.1.40

Cited by 44 publications

(17 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Systems performing sound event classification are usually evaluated in terms of accuracy [2,4,5,11,13,14]. Studies involving both monophonic and polyphonic sound event detection report results using a variety of metrics, for example Precision, Recall and F-score [6] or only F-score [7,26], recognition rate and false positive rate [3], or false positive and false negative rates [1].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Metrics for Polyphonic Sound Event Detection

2016

View full text Add to dashboard Cite

This paper presents and discusses various metrics proposed for evaluation of polyphonic sound event detection systems used in realistic situations where there are typically multiple sound sources active simultaneously. The system output in this case contains overlapping events, marked as multiple sounds detected as being active at the same time. The polyphonic system output requires a suitable procedure for evaluation against a reference. Metrics from neighboring fields such as speech recognition and speaker diarization can be used, but they need to be partially redefined to deal with the overlapping events. We present a review of the most common metrics in the field and the way they are adapted and interpreted in the polyphonic case. We discuss segment-based and event-based definitions of each metric and explain the consequences of instance-based and class-based averaging using a case study. In parallel, we provide a toolbox containing implementations of presented metrics.

show abstract

Section: Discussionmentioning

confidence: 99%

“…It has many applications in surveillance for security, healthcare and wildlife monitoring [1][2][3][4][5][6][7], and audio and video content based indexing and retrieval [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Metrics for Polyphonic Sound Event Detection

2016

View full text Add to dashboard Cite

show abstract

“…The aim of SED is to detect the onset and offset times for each sound event in an audio recording and associate a textual descriptor, i.e., a label for each of these events. SED has been drawing a surging amount of interest in recent years with applications including audio surveillance [1], healthcare monitoring [2], urban sound analysis [3], multimedia event detection [4] and bird call detection [5].…”

Section: Introductionmentioning

confidence: 99%

Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection

Çakır

Parascandolo

Heittola

et al. 2017

IEEE/ACM Trans. Audio Speech Lang. Process.

460

337

View full text Add to dashboard Cite

Abstract-Sound events often occur in unstructured environments where they exhibit wide variations in their frequency content and temporal structure. Convolutional neural networks (CNN) are able to extract higher level features that are invariant to local spectral and temporal variations. Recurrent neural networks (RNNs) are powerful in learning the longer term temporal context in the audio signals. CNNs and RNNs as classifiers have recently shown improved performances over established methods in various sound recognition tasks. We combine these two approaches in a Convolutional Recurrent Neural Network (CRNN) and apply it on a polyphonic sound event detection task. We compare the performance of the proposed CRNN method with CNN, RNN, and other established methods, and observe a considerable improvement for four different datasets consisting of everyday sound events.

show abstract

“…Within the EAR-IT use cases, a high temporal resolution to meet the event characteristics while having the possibility to respect for privacy related issues and low computational complexity of the VADs is desired. Furthermore, denoising functionality [15], foregroundbackground separation [12], filtering, channel selection and localization algorithms [16]- [18] may be part of the preprocessing stage with the goal to provide a high-quality audio signal representation to the consecutive acoustic event detection stage.…”

Section: B Preprocessingmentioning

confidence: 99%

Enhancing Wireless Sensor Networks with Acoustic Sensing Technology: Use Cases, Applications & Experiments

Hollosi

Nagy

Rodigast

et al. 2013

2013 IEEE International Conference on Green Computing and Communications and IEEE Internet of Things and IEEE Cyber, Physical A

Self Cite

View full text Add to dashboard Cite

This paper presents research carried out within the EU FP7 EAR-IT project, which is working on the challenges of bringing acoustic sensing intelligence to large-scale indoor and outdoor wireless sensor networks, i.e. into two existing testbeds out of the EU FP7 FIRE projects SmartSantander and Hobnet. Besides the benefits by integrating machine-learning based acoustic sensing technology, the general deployment approach of the so-called Acoustic Processing Unit, an embedded device whose capabilities go beyond state-of-the-art IoT sensors, as well as the EAR-IT indoor and outdoor use cases are described. This includes hardware qualification for the applications such as energy efficiency of buildings, traffic monitoring and emergency vehicle detection and tracking outdoor as well as acoustic emergency detection for indoor environments and further, a detailed description of the individual Acoustic Processing Unit software components. Latest efforts and simulation results for acoustic source localization using audio sensing technology for wireless sensor networks are presented, indicating that a more intelligent usage of the audio modality enables a wide range of applications and services with high social and technological value.

show abstract

Acoustic Monitoring and Localization for Social Care

Cited by 44 publications

References 14 publications

Metrics for Polyphonic Sound Event Detection

Metrics for Polyphonic Sound Event Detection

Convolutional Recurrent Neural Networks for Polyphonic Sound Event Detection

Enhancing Wireless Sensor Networks with Acoustic Sensing Technology: Use Cases, Applications & Experiments

Contact Info

Product

Resources

About