An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

This paper presents and discusses various metrics proposed for evaluation of polyphonic sound event detection systems used in realistic situations where there are typically multiple sound sources active simultaneously The system output in this case contains overlapping events, marked as multiple sounds detected as being active at the same time The polyphonic system output requires a suitable procedure for evaluation against a reference Metrics from neighboring fields such as speech recognition and speaker diarization can be used, but they need to be partially redefined to deal with the overlapping events We present a review of the most common metrics in the field and the way they are adapted and interpreted in the polyphonic case We discuss segment-based and event-based definitions of each metric and explain the consequences of instance-based and class-based averaging using a case study In parallel, we provide a toolbox containing implementations of presented metrics

Metrics for Polyphonic Sound Event Detection

https://www.jstage.jst.go.jp/article/jsprs1975/37/6/37_6_39/_pdf

1998 IEEE International Conference on SMCに参加して

The automatic recognition of sound events by computers is an important aspect of emerging applications such as automated surveillance, machine hearing and auditory scene understanding. Recent advances in machine learning, as well as in computational models of the human auditory system, have contributed to advances in this increasingly popular research field. Robust sound event classification, the ability to recognise sounds under real-world noisy conditions, is an especially challenging task. Classification methods translated from the speech recognition domain, using features such as mel-frequency cepstral coefficients, have been shown to perform reasonably well for the sound event classification task, although spectrogram-based or auditory image analysis techniques reportedly achieve superior performance in noise. This paper outlines a sound event classification framework that compares auditory image front end features with spectrogram image-based front end features, using support vector machine and deep neural network classifiers. Performance is evaluated on a standard robust classification task in different levels of corrupting noise, and with several system enhancements, and shown to compare very well with current state-of-the-art classification techniques.

/pdf/robust-sound-event-classification-using-deep-neural-networks-3o8zcrj38q.pdf

Robust sound event classification using deep neural networks

Traditional sound event recognition methods based on informative front end features such as MFCC, with back end sequencing methods such as HMM, tend to perform poorly in the presence of interfering acoustic noise. Since noise corruption may be unavoidable in practical situations, it is important to develop more robust features and classifiers. Recent advances in this field use powerful machine learning techniques with high dimensional input features such as spectrograms or auditory image. These improve robustness largely thanks to the discriminative capabilities of the back end classifiers. We extend this further by proposing novel features derived from spectrogram energy triggering, allied with the powerful classification capabilities of a convolutional neural network (CNN). The proposed method demonstrates excellent performance under noise-corrupted conditions when compared against state-of-the-art approaches on standard evaluation tasks. To the author's knowledge this in the first application of CNN in this field.

/pdf/robust-sound-event-recognition-using-convolutional-neural-10ale1iwb6.pdf

Robust sound event recognition using convolutional neural networks

The ability to automatically recognize a wide range of sound events in real-world conditions is an important part of applications such as acoustic surveillance and machine hearing. Our approach takes inspiration from both audio and image processing fields, and is based on transforming the sound into a two-dimensional representation, then extracting an image feature for classification. This provided the motivation for our previous work on the spectrogram image feature (SIF). In this paper, we propose a novel method to improve the sound event classification performance in severe mismatched noise conditions. This is based on the subband power distribution (SPD) image - a novel two-dimensional representation that characterizes the spectral power distribution over time in each frequency subband. Here, the high-powered reliable elements of the spectrogram are transformed to a localized region of the SPD, hence can be easily separated from the noise. We then extract an image feature from the SPD, using the same approach as for the SIF, and develop a novel missing feature classification approach based on a nearest neighbor classifier (kNN). We carry out comprehensive experiments on a database of 50 environmental sound classes over a range of challenging noise conditions. The results demonstrate that the SPD-IF is both discriminative over the broad range of sound classes, and robust in severe non-stationary noise.

Image Feature Representation of the Subband Power Distribution for Robust Sound Event Classification

There is much evidence to suggest that the human auditory system uses localised time-frequency information for the robust recognition of sounds. Despite this, conventional systems typically rely on features extracted from short windowed frames over time, covering the whole frequency spectrum. Such approaches are not inherently robust to noise, as each frame will contain a mixture of the spectral information from noise and signal. Here, we propose a novel approach based on the temporal coding of Local Spectrogram Features (LSFs), which generate spikes that are used to train a Spiking Neural Network (SNN) with temporal learning. LSFs represent robust location information in the spectrogram surrounding keypoints, which are detected in a signal-driven manner such that the effect of noise on the temporal coding is reduced. Our experiments demonstrate the robust performance of our approach across a variety of noise conditions, such that it is able to outperform the conventional frame-based baseline methods.

Temporal coding of local spectrogram features for robust sound recognition

Unlike other audio or speech signals, sound events have a relatively short time span. They are usually distinguished by their unique spectro-temporal signature. This paper proposes a novel classification method based on probabilistic distance support vector machines (SVMs). We study a parametric approach to characterizing sound signals using the distribution of the subband temporal envelope (STE), and kernel techniques for the subband probabilistic distance (SPD) under the framework of SVM. We show that generalized gamma modeling is well devised for sound characterization, and that the probabilistic distance kernel provides a closed form solution to the calculation of divergence distance, which tremendously reduces computational cost. We conducted experiments on a database of ten types of sound events. The results show that the proposed classification method significantly outperforms conventional SVM classifiers with Mel-frequency cepstral coefficients (MFCCs). The rapid computation of probabilistic distance also makes the proposed method an obvious choice for online sound event recognition.

Sound Event Recognition With Probabilistic Distance SVMs

Snoring is caused by the narrowing of the upper airway and it is excited by different locations within the upper airways. This irregularity could lead to the presence of Obstructive Sleep Apnea Syndrome (OSAS). Diagnosis of OSAS could therefore be made by snoring sound analysis. This paper proposes the novel method to automatically classify snoring sounds by their excitation locations for ComParE2017 challenge. We propose 3 sub-systems for classification. In the first system, we propose to integrate Bhattacharyya distance based Gaussian Mixture Model (GMM) supervectors to a set of static features provided by ComParE2017 challenge. The Bhattacharyya distance based GMM supervectors characterize the spectral dissimilarity measure among snore sounds excited by different locations. And, we employ Support Vector Machine (SVM) for classification. In the second system, we perform feature selection on static features provided by the challenge and conduct classification using Random Forest. In the third system, we extract spectrogram from audio and employ Convolutional Neural Network (CNN) for snore sound classification. Then, we fuse 3 sub-systems to produce final classification results. The experimental results show that the proposed system performs better than the challenge baseline.

An Integrated Solution for Snoring Sound Classification Using Bhattacharyya Distance Based GMM Supervectors with SVM, Feature Selection with Random Forest and Spectrogram with CNN.

This paper presents a novel method for sound event classification based on probabilistic distance SVM. The basic idea is to embed probabilistic distances into classical SVM to classify the sound events. The main point of this method is that the long-term characterization of sound events are better used in the classification compared to conventional method. Furthermore, taking into account the relative short time span of sound events, we develop a probabilistic distance SVM approach based on Hellinger distance from exponential modeling of temporal subband envelopes. An experiment on classifying 10 types of sound events was carried out and showed promising results of the proposed method compared to conventional methods.

Huy Dat Tran

Papers

Image Feature Representation of the Subband Power Distribution for Robust Sound Event Classification

Temporal coding of local spectrogram features for robust sound recognition

Sound Event Recognition With Probabilistic Distance SVMs

An Integrated Solution for Snoring Sound Classification Using Bhattacharyya Distance Based GMM Supervectors with SVM, Feature Selection with Random Forest and Spectrogram with CNN.

Probabilistic distance SVM with Hellinger-Exponential Kernel for sound event classification