Acoustic scene classification with matrix factorization for unsupervised feature learning

Bisot, Victor; Serizel, Romain; Essid, Slim; Richard, Gaël

doi:10.1109/icassp.2016.7472918

Cited by 64 publications

(54 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Acoustics is the science of production, control, transmission, response and the effects of sound. The classification of an acoustic scene allows devices to understand the environment and opens various applications [7]. For example, devices such as androids, IPhones, Internet devices, wearable devices, and robots prepared using artificial intelligence can benefit from the situations of the classification of the acoustic scene.…”

Section: A Acoustic Scene Classificationmentioning

confidence: 99%

Acoustic Classification using Deep Learning

Aslam¹,

Sarwar²,

Hanif³

et al. 2018

ijacsa

View full text Add to dashboard Cite

Abstract-Acoustic complements is an important methodology to perceive the sounds from environment. Significantly machines in different conditions can have the hearings capability like smartphones, different software or security systems. This kind of work can be implemented through conventional or deep learning machine models that contain revolutionized speech identification to understand general environment sounds. This work focuses on the acoustic classification and improves the performance of deep neural networks by using hybrid feature extraction methods. This study improves the efficiency of classification to extract features and make prediction of cost graph. We have adopted the hybrid feature extraction scheme consisting of DNN and CNN. The results have 12% improvement from the previous results by using mix feature extraction scheme.

show abstract

Section: A Acoustic Scene Classificationmentioning

confidence: 99%

Acoustic Classification using Deep Learning

Aslam¹,

Sarwar²,

Hanif³

et al. 2018

ijacsa

View full text Add to dashboard Cite

show abstract

“…However, since a lot of sound clips cannot always be collected, developing acoustic event and scene analyzing methods using a small-scale sound dataset is still an important problem. To analyze acoustic events and scenes from a small sound dataset, Bisot et al [52] and Komatsu et al [53] proposed methods based on non-negative matrix factorization (NMF). Kim et al [19] and Imoto et al [54] proposed acoustic scene analyzing methods based on acoustic topic models, which are Bayesian generative models of acoustic events from acoustic scenes.…”

Section: Acoustic Event and Scene Analysis For Small-scalementioning

confidence: 99%

Introduction to acoustic event and scene analysis

Imoto

2018

Acoust. Sci. & Tech.

View full text Add to dashboard Cite

show abstract

“…1 www.cs.tut.fi/sgn/arg/dcase2016/ or similar representations of audio by optimizing their parameters. Examples of such methods are Non-negative Matrix Factorization (NMF) [3] and CNNs [4]. In the scientific society there are many discussions about the use of feature engineering approaches versus feature learning methods.…”

Section: Introductionmentioning

confidence: 99%

A hybrid approach with multi-channel i-vectors and convolutional neural networks for acoustic scene classification

Eghbal-zadeh

Lehner

Dorfer

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-In Acoustic Scene Classification (ASC) two major approaches have been followed . While one utilizes engineered features such as mel-frequency-cepstral-coefficients (MFCCs), the other uses learned features that are the outcome of an optimization algorithm. I-vectors are the result of a modeling technique that usually takes engineered features as input. It has been shown that standard MFCCs extracted from monaural audio signals lead to i-vectors that exhibit poor performance, especially on indoor acoustic scenes. At the same time, Convolutional Neural Networks (CNNs) are well known for their ability to learn features by optimizing their filters. They have been applied on ASC and have shown promising results. In this paper, we first propose a novel multi-channel i-vector extraction scheme for ASC, improving their performance on indoor and outdoor scenes. Second, we propose a CNN architecture that achieves promising ASC results. Further, we show that i-vectors and CNNs capture complementary information from acoustic scenes. Finally, we propose a hybrid system for ASC using multi-channel i-vectors and CNNs by utilizing a score fusion technique. Using our method, we participated in the ASC task of the DCASE-2016 challenge. Our hybrid approach achieved 1 st rank among 49 submissions, substantially improving the previous state of the art.

show abstract

Acoustic scene classification with matrix factorization for unsupervised feature learning

Cited by 64 publications

References 18 publications

Acoustic Classification using Deep Learning

Acoustic Classification using Deep Learning

Introduction to acoustic event and scene analysis

A hybrid approach with multi-channel i-vectors and convolutional neural networks for acoustic scene classification

Contact Info

Product

Resources

About