The NeurIPS 2023 Machine Learning for Audio Workshop brings together machine learning (ML) experts from various audio domains. There are several valuable audio-driven ML tasks, from speech emotion recognition to audio event detection, but the community is sparse compared to other ML areas, e.g., computer vision or natural language processing. A major limitation with audio is the available data; with audio being a time-dependent modality, high-quality data collection is time-consuming and costly, making it challenging for academic groups to apply their often state-of-the-art strategies to a larger, more generalizable dataset. In this short white paper, to encourage researchers with limited access to large-datasets, the organizers first outline several open-source datasets that are available to the community, and for the duration of the workshop are making several propriety datasets available. Namely, three vocal datasets, Hume-Prosody, Hume-VocalBurst, an acted emotional speech dataset Modulate-Sonata, and an in-game streamer dataset Modulate-Stream. We outline the current baselines on these datasets but encourage researchers from across audio to utilize them outside of the initial baseline tasks.
There is a significant relevance of federated learning (FL) in the realm of Artificial Intelligence of Things (AIoT). However, most existing FL works are not conducted on datasets collected from authentic IoT devices that capture unique modalities and inherent challenges of IoT data. In this work, we introduce FedAIoT, an FL benchmark for AIoT to fill this critical gap. FedAIoT includes eight datatsets collected from a wide range of IoT devices. These datasets cover unique IoT modalities and target representative applications of AIoT. FedAIoT also includes a unified end-to-end FL framework for AIoT that simplifies benchmarking the performance of the datasets. Our benchmark results shed light on the opportunities and challenges of FL for AIoT. We hope FedAIoT could serve as an invaluable resource to foster advancements in the important field of FL for AIoT. The repository of FedAIoT is maintained at https://github.com/AIoT-MLSys-Lab/FedAIoT.
In this work, we propose GPT-FL, a generative pre-trained model-assisted federated learning (FL) framework. At its core, GPT-FL leverages generative pre-trained models to generate diversified synthetic data. These generated data are used to train a downstream model on the server, which is then fine-tuned with private client data under the standard FL framework. We show that GPT-FL consistently outperforms state-of-the-art FL methods in terms of model test accuracy, communication efficiency, and client sampling efficiency. Through comprehensive ablation analysis, we discover that the downstream model generated by synthetic data plays a crucial role in controlling the direction of gradient diversity during FL training, which enhances convergence speed and contributes to the notable accuracy boost observed with GPT-FL. Also, regardless of whether the target data falls within or outside the domain of the pre-trained generative model, GPT-FL consistently achieves significant performance gains, surpassing the results obtained by models trained solely with FL or synthetic data.
Federated learning (FL) has gained substantial attention in recent years due to the data privacy concerns related to the pervasiveness of consumer devices that continuously collect data from users. While a number of FL benchmarks have been developed to facilitate FL research, none of them include audio data and audio-related tasks. In this paper, we fill this critical gap by introducing a new FL benchmark for audio tasks which we refer to as FedAudio. FedAudio includes four representative and commonly used audio datasets from three important audio tasks that are well aligned with FL use cases. In particular, a unique contribution of FedAudio is the introduction of data noises and label errors to the datasets to emulate challenges when deploying FL systems in real-world settings. FedAudio also includes the benchmark results of the datasets and a PyTorch library with the objective of facilitating researchers to fairly compare their algorithms. We hope FedAudio could act as a catalyst to inspire new FL research for audio tasks and thus benefit the acoustic and speech research community. The datasets and benchmark results can be accessed at https://github.com/zhang-tuo-pdf/FedAudio.
Speech emotion recognition (SER) processes speech signals to detect and characterize expressed perceived emotions. Many SER application systems often acquire and transmit speech data collected at the client-side to remote cloud platforms for inference and decision making. However, speech data carry rich information not only about emotions conveyed in vocal expressions, but also other sensitive demographic traits such as gender, age and language background. Consequently, it is desirable for SER systems to have the ability to classify emotion constructs while preventing unintended/improper inferences of sensitive and demographic information. Federated learning (FL) is a distributed machine learning paradigm that coordinates clients to train a model collaboratively without sharing their local data. This training approach appears secure and can improve privacy for SER. However, recent works have demonstrated that FL approaches are still vulnerable to various privacy attacks like reconstruction attacks and membership inference attacks. Although most of these have focused on computer vision applications, such information leakages exist in the SER systems trained using the FL technique. To assess the information leakage of SER systems trained using FL, we propose an attribute inference attack framework that infers sensitive attribute information of the clients from shared gradients or model parameters, corresponding to the FedSGD and the FedAvg training algorithms, respectively. As a use case, we empirically evaluate our approach for predicting the client's gender information using three SER benchmark datasets: IEMOCAP, CREMA-D, and MSP-Improv. We show that the attribute inference attack is achievable for SER systems trained using FL. We further identify that most information leakage possibly comes from the first layer in the SER model.
Real-time magnetic resonance imaging (RT-MRI) of human speech production is enabling significant advances in speech science, linguistics, bio-inspired speech technology development, and clinical applications. Easy access to RT-MRI is however limited, and comprehensive datasets with broad access are needed to catalyze research across numerous domains. The imaging of the rapidly moving articulators and dynamic airway shaping during speech demands high spatio-temporal resolution and robust reconstruction methods. Further, while reconstructed images have been published, to-date there is no open dataset providing raw multi-coil RT-MRI data from an optimized speech production experimental setup. Such datasets could enable new and improved methods for dynamic image reconstruction, artifact correction, feature extraction, and direct extraction of linguistically-relevant biomarkers. The present dataset offers a unique corpus of 2D sagittal-view RT-MRI videos along with synchronized audio for 75 subjects performing linguistically motivated speech tasks, alongside the corresponding first-ever public domain raw RT-MRI data. The dataset also includes 3D volumetric vocal tract MRI during sustained speech sounds and high-resolution static anatomical T2-weighted upper airway MRI for each subject.
Spiral acquisitions are preferred in real-time MRI because of their efficiency, which has made it possible to capture vocal tract dynamics during natural speech. A fundamental limitation of spirals is blurring and signal loss due to off-resonance, which degrades image quality at air-tissue boundaries. Here, we present a new CNN-based off-resonance correction method that incorporates an attention-gate mechanism. This leverages spatial and channel relationships of filtered outputs and improves the expressiveness of the networks. We demonstrate improved performance with the attention-gate, on 1.5 Tesla spiral speech RT-MRI, compared to existing off-resonance correction methods.
Regularization is crucial to the success of many practical deep learning models, in particular in a more often than not scenario where there are only a few to a moderate number of accessible training samples. In addition to weight decay, data augmentation and dropout, regularization based on multi-branch architectures, such as Shake-Shake regularization, has been proven successful in many applications and attracted more and more attention. However, beyond model-based representation augmentation, it is unclear how Shake-Shake regularization helps to provide further improvement on classification tasks, let alone the baffling interaction between batch normalization and shaking. In this work, we present our investigation on Shake-Shake regularization, drawing connections to the vicinal risk minimization principle and discriminative feature learning in verification tasks. Furthermore, we identify a strong resemblance between batch normalized residual blocks and batch normalized recurrent neural networks, where both of them share a similar convergence behavior, which could be mitigated by a proper initialization of batch normalization. Based on the findings, our experiments on speech emotion recognition demonstrate simultaneously an improvement on the classification accuracy and a reduction on the generalization gap both with statistical significance.
Diversity or complementarity of experts in ensemble pattern recognition and information processing systems is widely-observed by researchers to be crucial for achieving performance improvement upon fusion. Understanding this link between ensemble diversity and fusion performance is thus an important research question. However, prior works have theoretically characterized ensemble diversity and have linked it with ensemble performance in very restricted settings. We present a generalized ambiguity decomposition (GAD) theorem as a broad framework for answering these questions. The GAD theorem applies to a generic convex ensemble of experts for any arbitrary twice-differentiable loss function. It shows that the ensemble performance approximately decomposes into a difference of the average expert performance and the diversity of the ensemble. It thus provides a theoretical explanation for the empirically-observed benefit of fusing outputs from diverse classifiers and regressors. It also provides a loss function-dependent, ensemble-dependent, and data-dependent definition of diversity. We present extensions of this decomposition to common regression and classification loss functions, and report a simulation-based analysis of the diversity term and the accuracy of the decomposition. We finally present experiments on standard pattern recognition data sets which indicate the accuracy of the decomposition for real-world classification and regression problems.