Audio-based context recognition

By Antti J. Eronen, Vesa T. Peltonen, Juha T. Tuomi, Anssi Klapuri, Seppo Fagerlund, Timo Sorsa, Gaetan Lorho, Jyri Huopaniemi. IEEE Transactions on Audio, Speech, and Language Processing, 2006

445 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/5858a8b27a5efa3c62a1adb1ede1f8cef9a80e88

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Signal Processing

Citations in the corpus

DCASE2017 Challenge Setup: Tasks, Datasets and Baseline System (2017, unknown): “…extract this information has huge potential in several applications, for example searching for multimedia based on its audio content [1], making context-aware mobile devices [2], robots, cars, etc., and intelligent monitoring systems [3, 4] to recognize activities using acoustic information.”
Acoustic Scene Classification: Classifying environments from the sounds they produce (2014, methodology): “3) Hidden Markov Models (HMMS): This class of models are used in several ASC systems [12], [20] to account for the temporal unfolding of events within complex soundscapes.”
Ambient Sound Provides Supervision for Visual Learning (2016, methodology): “Work in auditory scene analysis [6,7,23] meanwhile has provided computational methods for recognizing structures in audio streams.”
TUT database for acoustic scene classification and sound event detection (2016, background): “Results of acoustic scene classification range from 58% for 24 classes to 82% for 6 higher-level classes on the same data [2] to 93.”
Environmental Sound Recognition With Time–Frequency Audio Features (2009, background): “• Band Energy Ratio [11] : It is the ratio of the energy in a specific frequency-band to the total energy.”
Indoor localization without infrastructure using the acoustic background spectrum (2011, background): “performed only slightly worse than human listeners [12].”
Learning Sight from Sound: Ambient Sound Provides Supervision for Visual Learning (2017, unknown): “Work in auditory scene analysis (Ellis et al 2011; Eronen et al 2006; Lee et al 2010) meanwhile has provided computational methods for recognizing structures in audio streams.”
Acoustic event detection in real life recordings (2010, background): “In [3], authors compared various features and classifiers in classifying between 24 everyday contexts, such as restaurant, car, library, and office.”
Detection and Classification of Acoustic Scenes and Events (2015, background): “Alternative designs are possible, such as classiﬁcation with hierarchical labels [38], un-supervised clustering of audio scenes, or multi-label “auto-tag-ging” [39].”
Detection and Classification of Acoustic Scenes and Events: Outcome of the DCASE 2016 Challenge (2018, methodology): “eling aspect, methods range from classical statistical models like hidden Markov models (HMMs) [8], Gaussian mixture models”
Acoustic Scene Classification by Ensembling Gradient Boosting Machine and Convolutional Neural Networks (2017, methodology): “We have shown how a simple late fusion of them already brings substantial performance improvement, which demonstrates that they provide complementary information beneficial for ASC.”
High-level event recognition in unconstrained videos (2012, unknown): “[33] evaluated many audio features.”