Sound scene geotagging is a new topic of research which has evolved from acoustic scene classification. It is motivated by the idea of audio surveillance. Not content with only describing a scene in a recording, a machine which can locate where the recording was captured would be of use to many. In this paper we explore a series of common audio data augmentation methods to evaluate which best improves the accuracy of audio geotagging classifiers. Our work improves on the state-of-the-art city geotagging method by 23% in terms of classification accuracy.
We analyse multi-purpose audio using tools to visualise similarities within the data that may be observed via unsupervised methods. The success of machine learning classifiers is affected by the information contained within system inputs, so we investigate whether latent patterns within the data may explain performance limitations of such classifiers. We use the visual assessment of cluster tendency (VAT) technique on a well known data set to observe how the samples naturally cluster, and we make comparisons to the labels used for audio geotagging and acoustic scene classification. We demonstrate that VAT helps to explain and corroborate confusions observed in prior work to classify this audio, yielding greater insight into the performance - and limitations - of supervised classification systems. While this exploratory analysis is conducted on data for which we know the "ground truth" labels, this method of visualising the natural groupings as dictated by the data leads to important questions about unlabelled data that can help the evaluation and realistic expectations of future (including self-supervised) classification systems.
The great success of transformer-based models in natural language processing (NLP) has led to various attempts at adapting these architectures to other domains such as vision and audio. Recent work has shown that transformers can outperform Convolutional Neural Networks (CNNs) on vision and audio tasks. However, one of the main shortcomings of transformer models, compared to the well-established CNNs, is the computational complexity. In transformers, the compute and memory complexity is known to grow quadratically with the input length. Therefore, there has been extensive work on optimizing transformers, but often at the cost of degrading predictive performance. In this work, we propose a novel method to optimize and regularize transformers on audio spectrograms. Our proposed models achieve a new state-of-the-art performance on Audioset and can be trained on a single consumer-grade GPU. Furthermore, we propose a transformer model that outperforms CNNs in terms of both performance and training speed. Source code: https://github.com/kkoutini/PaSST
Underspecification and fairness in machine learning (ML) applications have recently become two prominent issues in the ML community. Acoustic scene classification (ASC) applications have so far remained unaffected by this discussion, but are now becoming increasingly used in real-world systems where fairness and reliability are critical aspects. In this work, we argue for the need of a more holistic evaluation process for ASC models through disaggregated evaluations. This entails taking into account performance differences across several factors, such as city, location, and recording device. Although these factors play a well-understood role in the performance of ASC models, most works report single evaluation metrics taking into account all different strata of a particular dataset. We argue that metrics computed on specific sub-populations of the underlying data contain valuable information about the expected real-world behaviour of proposed systems, and their reporting could improve the transparency and trustability of such systems. We demonstrate the effectiveness of the proposed evaluation process in uncovering underspecification and fairness problems exhibited by several standard ML architectures when trained on two widely-used ASC datasets. Our evaluation shows that all examined architectures exhibit large biases across all factors taken into consideration, and in particular with respect to the recording location. Additionally, different architectures exhibit different biases even though they are trained with the same experimental configurations.
Acoustic scene classification (ASC) aims to identify the type of scene (environment) in which a given audio signal is recorded. The log-mel feature and convolutional neural network (CNN) have recently become the most popular time-frequency (TF) feature representation and classifier in ASC. An audio signal recorded in a scene may include various sounds overlapping in time and frequency. The previous study suggests that separately considering the long-duration sounds and short-duration sounds in CNN may improve ASC accuracy. This study addresses the problem of the generalization ability of acoustic scene classifiers. In practice, acoustic scene signals' characteristics may be affected by various factors, such as the choice of recording devices and the change of recording locations. When an established ASC system predicts scene classes on audios recorded in unseen scenarios, its accuracy may drop significantly. The long-duration sounds not only contain domain-independent acoustic scene information, but also contain channel information determined by the recording conditions, which is prone to over-fitting. For a more robust ASC system, We propose a robust feature learning (RFL) framework to train the CNN. The RFL framework down-weights CNN learning specifically on long-duration sounds. The proposed method is to train an auxiliary classifier with only long-duration sound information as input. The auxiliary classifier is trained with an auxiliary loss function that assigns less learning weight to poorly classified examples than the standard cross-entropy loss. The experimental results show that the proposed RFL framework can obtain a more robust acoustic scene classifier towards unseen devices and cities.
We present an iVector based Acoustic Scene Classification (ASC) system suited for real life settings where active foreground speech can be present. In the proposed system, each recording is represented by a fixed-length iVector that models the recording's important properties. A regularized Gaussian backend classifier with class-specific covariance models is used to extract the relevant acoustic scene information from these iVectors. To alleviate the large performance degradation when a foreground speaker dominates the captured signal, we investigate the use of the iVector framework on Mel-Frequency Cepstral Coefficients (MFCCs) that are derived from an estimate of the noise power spectral density. This noise-floor can be extracted in a statistical manner for single channel recordings. We show that the use of noise-floor features is complementary to multi-condition training in which foreground speech is added to training signal to reduce the mismatch between training and testing conditions. Experimental results on the DCASE 2016 Task 1 dataset show that the noise-floor based features and multi-condition training realize significant classification accuracy gains of up to more than 25 percentage points (absolute) in the most adverse conditions. These promising results can further facilitate the integration of ASC in resource-constrained devices such as hearables.
Acoustic scene classification (ASC) is one of the most popular problems in the field of machine listening. The objective of this problem is to classify an audio clip into one of the predefined scenes using only the audio data. This problem has considerably progressed over the years in the different editions of DCASE. It usually has several subtasks that allow to tackle this problem with different approaches. The subtask presented in this report corresponds to a ASC problem that is constrained by the complexity of the model as well as having audio recorded from different devices, known as mismatch devices (real and simulated). The work presented in this report follows the research line carried out by the team in previous years. Specifically, a system based on two steps is proposed: a two-dimensional representation of the audio using the Gamamtone filter bank and a convolutional neural network using squeeze-excitation techniques. The presented system outperforms the baseline by about 17 percentage points.
Convolutional Neural Networks (CNNs) have been dominating classification tasks in various domains, such as machine vision, machine listening, and natural language processing. In machine listening, while generally exhibiting very good generalization capabilities, CNNs are sensitive to the specific audio recording device used, which has been recognized as a substantial problem in the acoustic scene classification (DCASE) community. In this study, we investigate the relationship between over-parameterization of acoustic scene classification models, and their resulting generalization abilities. Specifically, we test scaling CNNs in width and depth, under different conditions. Our results indicate that increasing width improves generalization to unseen devices, even without an increase in the number of parameters.
We propose a novel neural model compression strategy combining data augmentation, knowledge transfer, pruning, and quantization for device-robust acoustic scene classification (ASC). Specifically, we tackle the ASC task in a low-resource environment leveraging a recently proposed advanced neural network pruning mechanism, namely Lottery Ticket Hypothesis (LTH), to find a sub-network neural model associated with a small amount non-zero model parameters. The effectiveness of LTH for low-complexity acoustic modeling is assessed by investigating various data augmentation and compression schemes, and we report an efficient joint framework for low-complexity multi-device ASC, called \emph{Acoustic Lottery}. Acoustic Lottery could compress an ASC model up to $1/10^{4}$ and attain a superior performance (validation accuracy of 79.4% and Log loss of 0.64) compared to its not compressed seed model. All results reported in this work are based on a joint effort of four groups, namely GT-USTC-UKE-Tencent, aiming to address the "Low-Complexity Acoustic Scene Classification (ASC) with Multiple Devices" in the DCASE 2021 Challenge Task 1a.
This paper presents the details of Task 1A Acoustic Scene Classification in the DCASE 2021 Challenge. The task targeted development of low-complexity solutions with good generalization properties. The provided baseline system is based on a CNN architecture and post-training quantization of parameters. The system is trained using all the available training data, without any specific technique for handling device mismatch, and obtains an overall accuracy of 47.7%, with a log loss of 1.473. The task received 99 submissions from 30 teams, and most of the submitted systems outperformed the baseline. The most used techniques among the submissions were residual networks and weight quantization, with the top systems reaching over 70% accuracy, and log loss under 0.8. The acoustic scene classification task remained a popular task in the challenge, despite the increasing difficulty of the setup.
In this paper, we study the performance of variants of well-known Convolutional Neural Network (CNN) architectures on different audio tasks. We show that tuning the Receptive Field (RF) of CNNs is crucial to their generalization. An insufficient RF limits the CNN's ability to fit the training data. In contrast, CNNs with an excessive RF tend to over-fit the training data and fail to generalize to unseen testing data. As state-of-the-art CNN architectures-in computer vision and other domains-tend to go deeper in terms of number of layers, their RF size increases and therefore they degrade in performance in several audio classification and tagging tasks. We study well-known CNN architectures and how their building blocks affect their receptive field. We propose several systematic approaches to control the RF of CNNs and systematically test the resulting architectures on different audio classification and tagging tasks and datasets. The experiments show that regularizing the RF of CNNs using our proposed approaches can drastically improve the generalization of models, out-performing complex architectures and pre-trained models on larger datasets. The proposed CNNs achieve state-of-the-art results in multiple tasks, from acoustic scene classification to emotion and theme detection in music to instrument recognition, as demonstrated by top ranks in several pertinent challenges (DCASE, MediaEval).
Machine learning algorithms, when trained on audio recordings from a limited set of devices, may not generalize well to samples recorded using other devices with different frequency responses. In this work, a relatively straightforward method is introduced to address this problem. Two variants of the approach are presented. First requires aligned examples from multiple devices, the second approach alleviates this requirement. This method works for both time and frequency domain representations of audio recordings. Further, a relation to standardization and Cepstral Mean Subtraction is analysed. The proposed approach becomes effective even when very few examples are provided. This method was developed during the Detection and Classification of Acoustic Scenes and Events (DCASE) 2019 challenge and won the 1st place in the scenario with mis-matched recording devices with the accuracy of 75%. Source code for the experiments can be found online.
This paper presents the details of Task 1: Acoustic Scene Classification in the DCASE 2020 Challenge. The task consists of two subtasks: classification of data from multiple devices, requiring good generalization properties, and classification using low-complexity solutions. Here we describe the datasets and baseline systems. After the challenge submission deadline, challenge results and analysis of the submissions will be added.
Various attention mechanisms are being widely applied to acoustic scene classification. However, we empirically found that the attention mechanism can excessively discard potentially valuable information, despite improving performance. We propose the attentive max feature map that combines two effective techniques, attention and a max feature map, to further elaborate the attention mechanism and mitigate the above-mentioned phenomenon. We also explore various joint training methods, including multi-task learning, that allocate additional abstract labels for each audio recording. Our proposed system demonstrates state-of-the-art performance for single systems on Subtask A of the DCASE 2020 challenge by applying the two proposed techniques using relatively fewer parameters. Furthermore, adopting the proposed attentive max feature map, our team placed fourth in the recent DCASE 2021 challenge.
This paper provides an analysis of state-of-the-art activation functions with respect to supervised classification of deep neural network. These activation functions comprise of Rectified Linear Units (ReLU), Exponential Linear Unit (ELU), Scaled Exponential Linear Unit (SELU), Gaussian Error Linear Unit (GELU), and the Inverse Square Root Linear Unit (ISRLU). To evaluate, experiments over two deep learning network architectures integrating these activation functions are conducted. The first model, basing on Multilayer Perceptron (MLP), is evaluated with MNIST dataset to perform these activation functions. Meanwhile, the second model, likely VGGish-based architecture, is applied for Acoustic Scene Classification (ASC) Task 1A in DCASE 2018 challenge, thus evaluate whether these activation functions work well in different datasets as well as different network architectures.
In this paper, we present SpecAugment++, a novel data augmentation method for deep neural networks based acoustic scene classification (ASC). Different from other popular data augmentation methods such as SpecAugment and mixup that only work on the input space, SpecAugment++ is applied to both the input space and the hidden space of the deep neural networks to enhance the input and the intermediate feature representations. For an intermediate hidden state, the augmentation techniques consist of masking blocks of frequency channels and masking blocks of time frames, which improve generalization by enabling a model to attend not only to the most discriminative parts of the feature, but also the entire parts. Apart from using zeros for masking, we also examine two approaches for masking based on the use of other samples within the minibatch, which helps introduce noises to the networks to make them more discriminative for classification. The experimental results on the DCASE 2018 Task1 dataset and DCASE 2019 Task1 dataset show that our proposed method can obtain 3.6% and 4.7% accuracy gains over a strong baseline without augmentation (i.e. CP-ResNet) respectively, and outperforms other previous data augmentation methods.
Environmental sound analysis is currently getting more and more attentions. In the domain, acoustic scene classification and acoustic event classification are two closely related tasks. In this letter, a two-stage method is proposed for the above tasks. In the first stage, a mixup based MTL solution is proposed to classify both tasks in one single convolutional neural network. Artificial multi-label samples are used in the training of the MTL model, which are mixed up using existing single-task datasets. The multi-task model obtained can effectively recognize both the acoustic scenes and events. Compared with other methods such as re-annotation or synthesis, the mixup based MTL is low-cost, flexible and effective. In the second stage, the MTL model is modified into a single-task model which is fine-tuned using the original dataset corresponding to the specific task. By controlling the frozen layers carefully, the task-specific high level features are fused and the performance of the single classification task is further improved. The proposed method has confirmed the complementary characteristics of acoustic scene and acoustic event classifications. Finally, enhanced by ensemble learning, a satisfactory accuracy of 84.5 percent on TUT acoustic scene 2017 dataset and an accuracy of 77.5 percent on ESC-50 dataset are achieved respectively.
In acoustic scene classification (ASC), acoustic features play a crucial role in the extraction of scene information, which can be stored over different time scales. Moreover, the limited size of the dataset may lead to a biased model with a poor performance for records from unseen cities and confusing scene classes. In order to overcome this, we propose a long-term wavelet feature that requires a lower storage capacity and can be classified faster and more accurately compared with classic Mel filter bank coefficients (FBank). This feature can be extracted with predefined wavelet scales similar to the FBank. Furthermore, a novel data augmentation scheme based on generative adversarial neural networks with auxiliary classifiers (ACGANs) is adopted to improve the generalization of the ASC systems. The scheme, which contains ACGANs and a sample filter, extends the database iteratively by splitting the dataset, training the ACGANs and subsequently filtering samples. Experiments were conducted on datasets from the Detection and Classification of Acoustic Scenes and Events (DCASE) challenges. The results on the DCASE19 dataset demonstrate the improved performance of the proposed techniques compared with the classic FBank classifier. Moreover, the proposed fusion system achieved first place in the DCASE19 competition and surpassed the top accuracies on the DCASE17 dataset.
Acoustic scene classification systems using deep neural networks classify given recordings into pre-defined classes. In this study, we propose a novel scheme for acoustic scene classification which adopts an audio tagging system inspired by the human perception mechanism. When humans identify an acoustic scene, the existence of different sound events provides discriminative information which affects the judgement. The proposed framework mimics this mechanism using various approaches. Firstly, we employ three methods to concatenate tag vectors extracted using an audio tagging system with an intermediate hidden layer of an acoustic scene classification system. We also explore the multi-head attention on the feature map of an acoustic scene classification system using tag vectors. Experiments conducted on the detection and classification of acoustic scenes and events 2019 task 1-a dataset demonstrate the effectiveness of the proposed scheme. Concatenation and multi-head attention show a classification accuracy of 75.66 % and 75.58 %, respectively, compared to 73.63 % accuracy of the baseline. The system with the proposed two approaches combined demonstrates an accuracy of 76.75 %.
In this report, the Brno University of Technology (BUT) team submissions for Task 1 (Acoustic Scene Classification, ASC) of the DCASE-2019 challenge are described. Also, the analysis of different methods is provided. The proposed approach is a fusion of three different Convolutional Neural Network (CNN) topologies. The first one is a VGG like two-dimensional CNNs. The second one is again a two-dimensional CNN network which uses Max-Feature-Map activation and called Light-CNN (LCNN). The third network is a one-dimensional CNN which mainly used for speaker verification and called x-vector topology. All proposed networks use self-attention mechanism for statistic pooling. As a feature, we use a 256-dimensional log Mel-spectrogram. Our submissions are a fusion of several networks trained on 4-folds generated evaluation setup using different fusion strategies.