The open-set problem in acoustic scene classification

Battaglino, Daniele; Lepauloux, Ludovick; Evans, Nicholas

doi:10.1109/iwaenc.2016.7602939

Cited by 19 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Standard binary classifiers may fail to learn both baby cry (target) and non-baby cry (non-target) samples when these latter represent a subset of those encountered during testing. This problem has been identified as open-set and specific classifiers have therefore been employed [8,9].…”

Section: One-class Classifier -Svddmentioning

confidence: 99%

See 1 more Smart Citation

Baby Cry Sound Detection: A Comparison of Hand Crafted Features and Deep Learning Approach

Torres¹,

Battaglino

Lepauloux³

2017

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

Section: One-class Classifier -Svddmentioning

confidence: 99%

“…As expressed in [8,9], the detection in real conditions requires new types of classifiers more robust to unknown classes. In that sense the support vector data description (SVDD) is a good candidate for modeling baby cry features without being influenced by the number and the type of classes in the training set.…”

Section: Introductionmentioning

confidence: 99%

Baby Cry Sound Detection: A Comparison of Hand Crafted Features and Deep Learning Approach

Torres¹,

Battaglino

Lepauloux³

2017

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

“…Emerging real-world recognition systems require OSR to recognize unknown inputs and learn them when needed. There is a multitude of real-world application domains where OSR can play a role, such as cyber-physical systems, intrusion recognition, face identification, video tracking and surveillance, image and text classification, spam filtering, forensics linguistics, movie genre classification, and document tagging [143][144][145][146][147][148][149][150][151][152][153][154][155][156][157][158][159]. OSR is a challenging task in a large number of safety environments where even a small fraction of errors on unknowns could place human lives at risk, such as a self-driving car defect or robotic surgical assistants with flaws in perception and execution [160][161][162].…”

Section: Applications Of Open Set Recognitionmentioning

confidence: 99%

A Survey on Open Set Recognition

Mahdavi,

Carvalho

2021

Preprint

View full text Add to dashboard Cite

Recognition (OSR) is about dealing with unknown situations that were not learned by the models during training. In this paper, we provide a survey of existing works about OSR and distinguish their respective advantages and disadvantages to help out new researchers interested in the subject. The categorization of OSR models is provided along with an extensive summary of recent progress. Additionally, the relationships between OSR and its related tasks including multi-class classification and novelty detection are analyzed. It is concluded that OSR can appropriately deal with unknown instances in the real-world where capturing all possible classes in the training data is not practical. Lastly, applications of OSR are highlighted and some new directions for future research topics are suggested.

show abstract

“…In the audio domain, there have been few previous publications investigating open-set scenarios. Battaglino et al [16] applied the open-set method to audio scene classification, where a specific type of 1-class SVM has shown promising results for open-set recognition. Recently, Krstulovic [17] published a book chapter illustrating the importance of the open-set problem in the audio domain and investigating the restrictions of the existing evaluation practices, such as using F1-score, precision, and recall.…”

Section: Open-set Scenariomentioning

confidence: 99%

Open Set Audio Recognition for Multi-Class Classification With Rejection

Jleed

Bouchard

2020

IEEE Access

View full text Add to dashboard Cite

Most supervised audio recognition systems developed to this point have used a testing set which includes the same categories as the training set database. Such systems are called closed-set recognition (CSR). However, audio recognition in real applications can be more complicated, where the datasets can be dynamic, and novel categories can ceaselessly be detected. Hence, in practice, the usual methods will assign to these novel classes labels which are often incorrect. This work aims to investigate audio open-set recognition (OSR) suitable for multi-classes classification recognition, with a rejection option for classes never seen by the system. A probabilistic calibration of a support vector machine classifier is utilized and formulated under the open-set scenario. For this, it is proposed to apply a threshold technique called peak side ratio (PSR) to the audio recognition task. A candidate label is first examined by a Platt-calibrated support vector machine (SVM) to produce posterior probabilities. The PSR is then used to characterize the distribution of posterior probabilities values. This process helps to determine a threshold in order to reject or accept a particular class. Our proposed method is evaluated on different variations of open sets, using wellknown metrics. Experimental results reveal that our proposed method outperforms previous OSR approaches over a wide range of openness values.

show abstract

The open-set problem in acoustic scene classification

Cited by 19 publications

References 18 publications

Baby Cry Sound Detection: A Comparison of Hand Crafted Features and Deep Learning Approach

Baby Cry Sound Detection: A Comparison of Hand Crafted Features and Deep Learning Approach

A Survey on Open Set Recognition

Open Set Audio Recognition for Multi-Class Classification With Rejection

Contact Info

Product

Resources

About