Spiking Neural Networks (SNNs), as one of the algorithmic models in neuromorphic computing, have gained a great deal of research attention owing to temporal information processing capability, low power consumption, and high biological plausibility. The potential to efficiently extract spatio-temporal features makes it suitable for processing the event streams. However, existing synaptic structures in SNNs are almost full-connections or spatial 2D convolution, neither of which can extract temporal dependencies adequately. In this work, we take inspiration from biological synapses and propose a spatio-temporal synaptic connection SNN (STSC-SNN) model, to enhance the spatio-temporal receptive fields of synaptic connections, thereby establishing temporal dependencies across layers. Concretely, we incorporate temporal convolution and attention mechanisms to implement synaptic filtering and gating functions. We show that endowing synaptic models with temporal dependencies can improve the performance of SNNs on classification tasks. In addition, we investigate the impact of performance vias varied spatial-temporal receptive fields and reevaluate the temporal modules in SNNs. Our approach is tested on neuromorphic datasets, including DVS128 Gesture (gesture recognition), N-MNIST, CIFAR10-DVS (image classification), and SHD (speech digit recognition). The results show that the proposed model outperforms the state-of-the-art accuracy on nearly all datasets.
The audio spectrogram is a time-frequency representation that has been widely used for audio classification. One of the key attributes of the audio spectrogram is the temporal resolution, which depends on the hop size used in the Short-Time Fourier Transform (STFT). Previous works generally assume the hop size should be a constant value (e.g., 10 ms). However, a fixed temporal resolution is not always optimal for different types of sound. The temporal resolution affects not only classification accuracy but also computational cost. This paper proposes a novel method, DiffRes, that enables differentiable temporal resolution modeling for audio classification. Given a spectrogram calculated with a fixed hop size, DiffRes merges non-essential time frames while preserving important frames. DiffRes acts as a "drop-in" module between an audio spectrogram and a classifier and can be jointly optimized with the classification task. We evaluate DiffRes on five audio classification tasks, using mel-spectrograms as the acoustic features, followed by off-the-shelf classifier backbones. Compared with previous methods using the fixed temporal resolution, the DiffRes-based method can achieve the equivalent or better classification accuracy with at least 25% computational cost reduction. We further show that DiffRes can improve classification accuracy by increasing the temporal resolution of input acoustic features, without adding to the computational cost.
Recently, there has been increasing interest in building efficient audio neural networks for on-device scenarios. Most existing approaches are designed to reduce the size of audio neural networks using methods such as model pruning. In this work, we show that instead of reducing model size using complex methods, eliminating the temporal redundancy in the input audio features (e.g., mel-spectrogram) could be an effective approach for efficient audio classification. To do so, we proposed a family of simple pooling front-ends (SimPFs) which use simple non-parametric pooling operations to reduce the redundant information within the mel-spectrogram. We perform extensive experiments on four audio classification tasks to evaluate the performance of SimPFs. Experimental results show that SimPFs can achieve a reduction in more than half of the number of floating point operations (FLOPs) for off-the-shelf audio neural networks, with negligible degradation or even some improvements in audio classification performance.
Spiking Neural Networks (SNNs) provide an efficient computational mechanism for temporal signal processing, especially when coupled with low-power SNN inference ASICs. SNNs have been historically difficult to configure, lacking a general method for finding solutions for arbitrary tasks. In recent years, gradient-descent optimization methods have been applied to SNNs with increasing ease. SNNs and SNN inference processors therefore offer a good platform for commercial low-power signal processing in energy constrained environments without cloud dependencies. However, to date these methods have not been accessible to ML engineers in industry, requiring graduate-level training to successfully configure a single SNN application. Here we demonstrate a convenient high-level pipeline to design, train and deploy arbitrary temporal signal processing applications to sub-mW SNN inference hardware. We apply a new straightforward SNN architecture designed for temporal signal processing, using a pyramid of synaptic time constants to extract signal features at a range of temporal scales. We demonstrate this architecture on an ambient audio classification task, deployed to the Xylo SNN inference processor in streaming mode. Our application achieves high accuracy (98%) and low latency (100ms) at low power (<100$\mu$W inference power). Our approach makes training and deploying SNN applications available to ML engineers with general NN backgrounds, without requiring specific prior experience with spiking NNs. We intend for our approach to make Neuromorphic hardware and SNNs an attractive choice for commercial low-power and edge signal processing applications.
Due to the increased demand for music streaming/recommender services and the recent developments of music information retrieval frameworks, Music Genre Classification (MGC) has attracted the community's attention. However, convolutional-based approaches are known to lack the ability to efficiently encode and localize temporal features. In this paper, we study the broadcast-based neural networks aiming to improve the localization and generalizability under a small set of parameters (about 180k) and investigate twelve variants of broadcast networks discussing the effect of block configuration, pooling method, activation function, normalization mechanism, label smoothing, channel interdependency, LSTM block inclusion, and variants of inception schemes. Our computational experiments using relevant datasets such as GTZAN, Extended Ballroom, HOMBURG, and Free Music Archive (FMA) show state-of-the-art classification accuracies in Music Genre Classification. Our approach offers insights and the potential to enable compact and generalizable broadcast networks for music and audio classification.
The purpose of this paper is to compare different learnable frontends in medical acoustics tasks. A framework has been implemented to classify human respiratory sounds and heartbeats in two categories, i.e. healthy or affected by pathologies. After obtaining two suitable datasets, we proceeded to classify the sounds using two learnable state-of-art frontends -- LEAF and nnAudio -- plus a non-learnable baseline frontend, i.e. Mel-filterbanks. The computed features are then fed into two different CNN models, namely VGG16 and EfficientNet. The frontends are carefully benchmarked in terms of the number of parameters, computational resources, and effectiveness. This work demonstrates how the integration of learnable frontends in neural audio classification systems may improve performance, especially in the field of medical acoustics. However, the usage of such frameworks makes the needed amount of data even larger. Consequently, they are useful if the amount of data available for training is adequately large to assist the feature learning process.
Conventional audio-visual models have independent audio and video branches. In this work, we unify the audio and visual branches by designing a Unified Audio-Visual Model (UAVM). The UAVM achieves a new state-of-the-art audio-visual event classification accuracy of 65.8% on VGGSound. More interestingly, we also find a few intriguing properties of UAVM that the modality-independent counterparts do not have.
This paper studies a simple extension of image-based Masked Autoencoders (MAE) to self-supervised representation learning from audio spectrograms. Following the Transformer encoder-decoder design in MAE, our Audio-MAE first encodes audio spectrogram patches with a high masking ratio, feeding only the non-masked tokens through encoder layers. The decoder then re-orders and decodes the encoded context padded with mask tokens, in order to reconstruct the input spectrogram. We find it beneficial to incorporate local window attention in the decoder, as audio spectrograms are highly correlated in local time and frequency bands. We then fine-tune the encoder with a lower masking ratio on target datasets. Empirically, Audio-MAE sets new state-of-the-art performance on six audio and speech classification tasks, outperforming other recent models that use external supervised pre-training. The code and models will be at https://github.com/facebookresearch/AudioMAE.
In audio classification, differentiable auditory filterbanks with few parameters cover the middle ground between hard-coded spectrograms and raw audio. LEAF (arXiv:2101.08596), a Gabor-based filterbank combined with Per-Channel Energy Normalization (PCEN), has shown promising results, but is computationally expensive. With inhomogeneous convolution kernel sizes and strides, and by replacing PCEN with better parallelizable operations, we can reach similar results more efficiently. In experiments on six audio classification tasks, our frontend matches the accuracy of LEAF at 3% of the cost, but both fail to consistently outperform a fixed mel filterbank. The quest for learnable audio frontends is not solved.
Although deep Neural Networks (DNNs) have achieved tremendous success in audio classification tasks, their uncertainty calibration are still under-explored. A well-calibrated model should be accurate when it is certain about its prediction and indicate high uncertainty when it is likely to be inaccurate. In this work, we investigate the uncertainty calibration for deep audio classifiers. In particular, we empirically study the performance of popular calibration methods: (i) Monte Carlo Dropout, (ii) ensemble, (iii) focal loss, and (iv) spectral-normalized Gaussian process (SNGP), on audio classification datasets. To this end, we evaluate (i-iv) for the tasks of environment sound and music genre classification. Results indicate that uncalibrated deep audio classifiers may be over-confident, and SNGP performs the best and is very efficient on the two datasets of this paper.
Spiking neural networks (SNNs) underlie low-power, fault-tolerant information processing in the brain and could constitute a power-efficient alternative to conventional deep neural networks when implemented on suitable neuromorphic hardware accelerators. However, instantiating SNNs that solve complex computational tasks in-silico remains a significant challenge. Surrogate gradient (SG) techniques have emerged as a standard solution for training SNNs end-to-end. Still, their success depends on synaptic weight initialization, similar to conventional artificial neural networks (ANNs). Yet, unlike in the case of ANNs, it remains elusive what constitutes a good initial state for an SNN. Here, we develop a general initialization strategy for SNNs inspired by the fluctuation-driven regime commonly observed in the brain. Specifically, we derive practical solutions for data-dependent weight initialization that ensure fluctuation-driven firing in the widely used leaky integrate-and-fire (LIF) neurons. We empirically show that SNNs initialized following our strategy exhibit superior learning performance when trained with SGs. These findings generalize across several datasets and SNN architectures, including fully connected, deep convolutional, recurrent, and more biologically plausible SNNs obeying Dale's law. Thus fluctuation-driven initialization provides a practical, versatile, and easy-to-implement strategy for improving SNN training performance on diverse tasks in neuromorphic engineering and computational neuroscience.
Spiking neural networks (SNNs), particularly the single-spike variant in which neurons spike at most once, are considerably more energy efficient than standard artificial neural networks (ANNs). However, single-spike SSNs are difficult to train due to their dynamic and non-differentiable nature, where current solutions are either slow or suffer from training instabilities. These networks have also been critiqued for their limited computational applicability such as being unsuitable for time-series datasets. We propose a new model for training single-spike SNNs which mitigates the aforementioned training issues and obtains competitive results across various image and neuromorphic datasets, with up to a $13.98\times$ training speedup and up to an $81\%$ reduction in spikes compared to the multi-spike SNN. Notably, our model performs on par with multi-spike SNNs in challenging tasks involving neuromorphic time-series datasets, demonstrating a broader computational role for single-spike SNNs than previously believed.
Most curriculum learning methods require an approach to sort the data samples by difficulty, which is often cumbersome to perform. In this work, we propose a novel curriculum learning approach termed Learning Rate Curriculum (LeRaC), which leverages the use of a different learning rate for each layer of a neural network to create a data-agnostic curriculum during the initial training epochs. More specifically, LeRaC assigns higher learning rates to neural layers closer to the input, gradually decreasing the learning rates as the layers are placed farther away from the input. The learning rates increase at various paces during the first training iterations, until they all reach the same value. From this point on, the neural model is trained as usual. This creates a model-level curriculum learning strategy that does not require sorting the examples by difficulty and is compatible with any neural network, generating higher performance levels regardless of the architecture. We conduct comprehensive experiments on 12 data sets from the computer vision (CIFAR-10, CIFAR-100, Tiny ImageNet, ImageNet-200, Food-101, UTKFace, PASCAL VOC), language (BoolQ, QNLI, RTE) and audio (ESC-50, CREMA-D) domains, considering various convolutional (ResNet-18, Wide-ResNet-50, DenseNet-121, YOLOv5), recurrent (LSTM) and transformer (CvT, BERT, SepTr) architectures. We compare our approach with the conventional training regime, as well as with Curriculum by Smoothing (CBS), a state-of-the-art data-agnostic curriculum learning approach. Unlike CBS, our performance improvements over the standard training regime are consistent across all data sets and models. Furthermore, we significantly surpass CBS in terms of training time (there is no additional cost over the standard training regime for LeRaC). Our code is freely available at: https://github.com/CroitoruAlin/LeRaC.
Recognizing human non-speech vocalizations is an important task and has broad applications such as automatic sound transcription and health condition monitoring. However, existing datasets have a relatively small number of vocal sound samples or noisy labels. As a consequence, state-of-the-art audio event classification models may not perform well in detecting human vocal sounds. To support research on building robust and accurate vocal sound recognition, we have created a VocalSound dataset consisting of over 21,000 crowdsourced recordings of laughter, sighs, coughs, throat clearing, sneezes, and sniffs from 3,365 unique subjects. Experiments show that the vocal sound recognition performance of a model can be significantly improved by 41.9% by adding VocalSound dataset to an existing dataset as training material. In addition, different from previous datasets, the VocalSound dataset contains meta information such as speaker age, gender, native language, country, and health condition.
Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design. Each parameters configuration of a synthesizer produces a unique timbre and can be viewed as a unique instrument. The problem of estimating a set of parameters configuration that best restore a sound timbre is an important yet complicated problem, i.e.: the synthesizer parameters estimation problem. We proposed a multi-modal deep-learning-based pipeline Sound2Synth, together with a network structure Prime-Dilated Convolution (PDC) specially designed to solve this problem. Our method achieved not only SOTA but also the first real-world applicable results on Dexed synthesizer, a popular FM synthesizer.
Self-supervised learning (SSL) learns knowledge from a large amount of unlabeled data, and then transfers the knowledge to a specific problem with a limited number of labeled data. SSL has achieved promising results in various domains. This work addresses the problem of segment-level general audio SSL, and proposes a new transformer-based teacher-student SSL model, named ATST. A transformer encoder is developed on a recently emerged teacher-student baseline scheme, which largely improves the modeling capability of pre-training. In addition, a new strategy for positive pair creation is designed to fully leverage the capability of transformer. Extensive experiments have been conducted, and the proposed model achieves the new state-of-the-art results on almost all of the downstream tasks.
While efficient architectures and a plethora of augmentations for end-to-end image classification tasks have been suggested and heavily investigated, state-of-the-art techniques for audio classifications still rely on numerous representations of the audio signal together with large architectures, fine-tuned from large datasets. By utilizing the inherited lightweight nature of audio and novel audio augmentations, we were able to present an efficient end-to-end network with strong generalization ability. Experiments on a variety of sound classification sets demonstrate the effectiveness and robustness of our approach, by achieving state-of-the-art results in various settings. Public code is available at: \href{https://github.com/Alibaba-MIIL/AudioClassfication}{this http url}
Spiking Neural Network (SNN) is considered more biologically realistic and power-efficient as it imitates the fundamental mechanism of the human brain. Recently, backpropagation (BP) based SNN learning algorithms that utilize deep learning frameworks have achieved good performance. However, bio-interpretability is partially neglected in those BP-based algorithms. Toward bio-plausible BP-based SNNs, we consider three properties in modeling spike activities: Multiplicity, Adaptability, and Plasticity (MAP). In terms of multiplicity, we propose a Multiple-Spike Pattern (MSP) with multiple spike transmission to strengthen model robustness in discrete time-iteration. To realize adaptability, we adopt Spike Frequency Adaption (SFA) under MSP to decrease spike activities for improved efficiency. For plasticity, we propose a trainable convolutional synapse that models spike response current to enhance the diversity of spiking neurons for temporal feature extraction. The proposed SNN model achieves competitive performances on neuromorphic datasets: N-MNIST and SHD. Furthermore, experimental results demonstrate that the proposed three aspects are significant to iterative robustness, spike efficiency, and temporal feature extraction capability of spike activities. In summary, this work proposes a feasible scheme for bio-inspired spike activities with MAP, offering a new neuromorphic perspective to embed biological characteristics into spiking neural networks.
Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based benchmarks by offering the first comprehensive, public and fully reproducible audio based alternative, covering a variety of sound domains and experimental settings. We compare the few-shot classification performance of a variety of techniques on seven audio datasets (spanning environmental sounds to human-speech). Extending this, we carry out in-depth analyses of joint training (where all datasets are used during training) and cross-dataset adaptation protocols, establishing the possibility of a generalised audio few-shot classification algorithm. Our experimentation shows gradient-based meta-learning methods such as MAML and Meta-Curvature consistently outperform both metric and baseline methods. We also demonstrate that the joint training routine helps overall generalisation for the environmental sound databases included, as well as being a somewhat-effective method of tackling the cross-dataset/domain setting.
In this paper, we propose a simple yet powerful improvement over the recent Self-Supervised Audio Spectrogram Transformer (SSAST) model for speech and audio classification. Specifically, we leverage the insight that the SSAST uses a very high masking ratio (75%) during pretraining, meaning that the vast majority of self-attention compute is performed on mask tokens. We address this by integrating the encoder-decoder architecture from Masked Autoencoders are Scalable Vision Learners (MAE) into the SSAST, where a deep encoder operates on only unmasked input, and a shallow decoder operates on encoder outputs and mask tokens. We find that MAE-like pretraining can provide a 3x speedup and 2x memory usage reduction over the vanilla SSAST using current audio pretraining strategies with ordinary model and input sizes. When fine-tuning on downstream tasks, which only uses the encoder, we find that our approach outperforms the SSAST on a variety of downstream tasks. We further conduct comprehensive evaluations into different strategies of pretraining and explore differences in MAE-style pretraining between the visual and audio domains.