NMF-Based Spectral Analysis for Acoustic Event Classification Tasks

Ludeña-Choez, Jimmy; Gallardo-Antolín, Ascensión

doi:10.1007/978-3-642-38847-7_2

Cited by 3 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Kullback-Leibler divergence results in a non-negative quantity and is unbounded. In this work, the KL divergence is considered because it has recently been used, with good results, in audio processing tasks such as speech enhancement and denoising for automatic speech recognition [ 21 , 28 ], feature extraction [ 22 ] or acoustic event classification [ 22 , 29 ]. To find a local optimum value for the KL divergence between V and ( W H ), an iterative scheme with multiplicative update rules can be used as proposed in [ 27 ] and stated in Eqs ( 3 ) and ( 4 ), where 1 is a matrix of size V , whose elements are all ones, and the multiplications ⊗ and divisions are component-wise operations.…”

Section: Methodsmentioning

confidence: 99%

Bird sound spectrogram decomposition through Non-Negative Matrix Factorization for the acoustic classification of bird species

2017

Self Cite

View full text Add to dashboard Cite

Feature extraction for Acoustic Bird Species Classification (ABSC) tasks has traditionally been based on parametric representations that were specifically developed for speech signals, such as Mel Frequency Cepstral Coefficients (MFCC). However, the discrimination capabilities of these features for ABSC could be enhanced by accounting for the vocal production mechanisms of birds, and, in particular, the spectro-temporal structure of bird sounds. In this paper, a new front-end for ABSC is proposed that incorporates this specific information through the non-negative decomposition of bird sound spectrograms. It consists of the following two different stages: short-time feature extraction and temporal feature integration. In the first stage, which aims at providing a better spectral representation of bird sounds on a frame-by-frame basis, two methods are evaluated. In the first method, cepstral-like features (NMF_CC) are extracted by using a filter bank that is automatically learned by means of the application of Non-Negative Matrix Factorization (NMF) on bird audio spectrograms. In the second method, the features are directly derived from the activation coefficients of the spectrogram decomposition as performed through NMF (H_CC). The second stage summarizes the most relevant information contained in the short-time features by computing several statistical measures over long segments. The experiments show that the use of NMF_CC and H_CC in conjunction with temporal integration significantly improves the performance of a Support Vector Machine (SVM)-based ABSC system with respect to conventional MFCC.

show abstract

Section: Methodsmentioning

confidence: 99%

Bird sound spectrogram decomposition through Non-Negative Matrix Factorization for the acoustic classification of bird species

2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…The AEC system is based on a one-against-one SVM with Radial Basis Function (RBF) kernel on normalized features (Ludeña-Choez & Gallardo-Antolín, 2013b, 2015. The system was developed using the LIBSVM software (Chang & Lin, 2011).…”

Section: Database and Baseline Systemmentioning

confidence: 99%

“…Many state-of-the art front-ends are composed of two modules: short-time feature extraction, in which acoustic coe cients are computed on a frame-byframe basis (typically, the frame period used for speech/audio analysis is about 10-20 ms) from analysis windows of 20-40 ms, and temporal feature integration (Meng et al, 2007), in which features at larger time scales are extracted by combining somehow the short-time characteristics information over a longer time-frame composed of several consecutive frames. The resulting characteristics are often called segmental features (Zhang & Schuller, 2012;Ludeña-Choez & Gallardo-Antolín, 2013a, 2015. In this paper, two techniques which improve the performance of each of these modules by taking into account the specific spectro-temporal structure of acoustic events are presented.…”

Section: Introductionmentioning

confidence: 99%