Deep Scalogram Representations for Acoustic Scene Classification

Abstract

Spectrogram representations of acoustic scenes have achieved competitive performance for acoustic scene classification. Yet, the spectrogram alone does not take into account a substantial amount of time-frequency information. In this study, we present an approach for exploring the benefits of deep scalogram representations, extracted in segments from an audio stream. The approach presented firstly transforms the segmented acoustic scenes into bump and morse scalograms, as well as spectrograms; secondly, the spectrograms or scalograms are sent into pre-trained convolutional neural networks; thirdly, the features extracted from a subsequent fully connected layer are fed into (bidirectional) gated recurrent neural networks, which are followed by a single highway layer and a softmax layer; finally, predictions from these three systems are fused by a margin sampling value strategy. We then evaluate the proposed approach using the acoustic scene classification data set of 2017 IEEE AASP Challenge on Detection and Classification of Acoustic Scenes and Events (DCASE). On the evaluation set, an accuracy of 64.0 % % % from bidirectional gated recurrent neural networks is obtained when fusing the spectrogram and the bump scalogram, which is an improvement on the 61.0 % % % baseline result provided by the DCASE 2017 organisers. This result shows that extracted bump scalograms are capable of improving the classification accuracy, when fusing with a spectrogram-based system.

Environment Sound Event Classification With a Two-Stream Convolutional Neural Network

“…In our future work, other newly developed models, e.g. [24] and [29], will be considered to explore the better recognation method in the field of ESC.…”

“…The deep learning models represented by the CNN and Long Short-Term Memory (LSTM) have been widely used in the field of audio processing [22]- [24]. However, we only chose the CNN to construct the basic model of ESC, because the CNN has a many advantages over LSTM in ESC tasks.…”

Partial Discharge Classification Using Deep Learning Methods—Survey of Recent Progress

“…A more ideal concept would be to use the raw pulses registered by the sensor, as some authors have done, using a single pulse waveform or several consecutives pulses recorded over time, or transforming the pulses into a spectrogram image. Other representations could also be investigated to avoid limitations imposed by the STFT in the spectrogram representation, as the Local Polynomial Fourier Transform [32] or a scalogram [33].…”

Putting Together Wavelet-based Scaleograms and Convolutional Neural Networks for Anomaly Detection in Nuclear Reactors

“…For example, complex spectrograms have been used to train a speech-enhancement CNN model, which denoises the input signals [14]. In the field of acoustic scene classification, a DL approach based on scaleograms and spectrograms paired with a pretrained CNN and a generalized regression neural network has been proposed in [30], providing excellent results in the DCASE 2017 challenge [28]. Besides that, DL methods have been applied to speech emotion recognition problems.…”