Recurrence quantification analysis features for environmental sound recognition

Roma, Gerard; Nogueira, Waldo; Herrera, Perfecto

doi:10.1109/waspaa.2013.6701890

Cited by 43 publications

(45 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, most of the leading results were obtained by those who captured medium-range temporal information in the features used for classification. Four of the five highest-scoring systems did this: Roma et al [56] captured temporal repetition and similarity using "recurrence quantification analysis"; Rakotomamonjy and Gasso [55] used gradient features from image-processing; Geiger et al [48] extracted features from linear regression over time; Chum et al [46] trained a HMM. Each of these is a generic statistical model for temporal evolution, whose fitted parameters can then be used as features for classification.…”

Section: A Sc Resultsmentioning

confidence: 99%

Detection and Classification of Acoustic Scenes and Events

Stowell

Giannoulis

Benetos

et al. 2015

IEEE Trans. Multimedia

445

332

View full text Add to dashboard Cite

International audience—For intelligent systems to make best use of the audio modality, it is important that they can recognize not just speech and music, which have been researched as specific tasks, but also general sounds in everyday environments. To stimulate research in this field we conducted a public research challenge: the IEEE Audio and Acoustic Signal Processing Technical Committee challenge on Detection and Classification of Acoustic Scenes and Events (DCASE). In this paper, we report on the state of the art in automatically classifying audio scenes, and automatically detecting and classifying audio events. We survey prior work as well as the state of the art represented by the submissions to the challenge from various research groups. We also provide detail on the organization of the challenge, so that our experience as challenge hosts may be useful to those organizing challenges in similar domains. We created new audio datasets and baseline systems for the challenge; these, as well as some submitted systems, are publicly available under open licenses, to serve as benchmarks for further research in general-purpose machine listening

show abstract

Section: A Sc Resultsmentioning

confidence: 99%

Detection and Classification of Acoustic Scenes and Events

Stowell

Giannoulis

Benetos

et al. 2015

IEEE Trans. Multimedia

445

332

View full text Add to dashboard Cite

show abstract

“…Method CPS [59] Segmentation -Likelihood ratio test classification DHV [60], [61] MFCCs (features) -HMMs (detection) GVV [62], [63] NMF (detection) -HMMs (postprocessing) NVM [64], [65] Hierarchical HMMs + Random Forests (classification) NR [66], [67] MFCCs (features) -SVMs (classification) SCS [68], [69] Gabor filterbank (features) -HMMs (classification) VVK [62], [70] MFCCs (features) -GMMs (detection) Baseline [14] NMF with learned bases (detection) Test set and the simulated sets QMUL Instance and QMUL Abstract. The baseline, CPS, GVV and SCS systems performed equivalently across the 2 datasets.…”

Section: Systemmentioning

confidence: 99%

A Morphological Model for Simulating Acoustic Scenes and Its Application to Sound Event Detection

Lafay

Lagrange

Rossignol

et al. 2016

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

“…Features extracted from time-frequency decompositions based on matching pursuit have also been evaluated [8], [9]. Among hand-crafted features that have shown some successes in providing discriminative information about audio scenes, we can also mention recurrence quantitative analysis (RQA) [10] which aims at capturing some recurring patterns in MFCC representations. Since, in most cases, the first step when classifying acoustic scenes is to compute a 2D time-frequency representation, some works have investigated features that are typically used in computer vision such as histogram of gradient (HOG) [2], [11], local binary pattern [12] or texturebased features [13], [14].…”

Section: Introductionmentioning

confidence: 99%

Supervised Representation Learning for Audio Scene Classification

Rakotomamonjy

2017

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Abstract-This paper investigates the use of supervised feature learning approaches for extracting relevant and discriminative features from acoustic scene recordings. Owing to the recent release of open datasets for acoustic scene classification (ASC) problems, representation learning techniques can now be envisioned for solving the problem of feature extraction. This paper makes a step towards this goal by first studying models based on convolutional neural networks (ConvNet). Because the scale of the datasets available is still small compared to those available in computer vision, we also introduce a technical contribution denoted as supervised non-negative matrix factorization (SNMF). Our goal through this SNMF is to induce the matrix decomposition to carry out discriminative information in addition to the usual generative ones. We achieve this objective by augmenting the NMF optimization problem with a novel loss function related to class labels of acoustic scenes. Our experiments show that despite the small-scale setting, supervised feature learning is favorably competitive compared to the current state-of-the-art features. We also point out that for smaller scale dataset, supervised NMF is indeed slightly less prone to overfitting than convolutional neural networks. While the performances of these learned features are interesting per se, a deeper analysis of their behavior in the acoustic scene problem context raises open and difficult questions that we believe, need to be addressed for further performance breakthroughs.

show abstract

Recurrence quantification analysis features for environmental sound recognition

Cited by 43 publications

References 8 publications

Detection and Classification of Acoustic Scenes and Events

Detection and Classification of Acoustic Scenes and Events

A Morphological Model for Simulating Acoustic Scenes and Its Application to Sound Event Detection

Supervised Representation Learning for Audio Scene Classification

Contact Info

Product

Resources

About