BiSSL: Bilevel Optimization for Self-Supervised Pre-Training and Fine-Tuning

In this work, we present BiSSL, a first-of-its-kind training framework that introduces bilevel optimization to enhance the alignment between the pretext pre-training and downstream fine-tuning stages in self-supervised learning. BiSSL formulates the pretext and downstream task objectives as the lower- and upper-level objectives in a bilevel optimization problem and serves as an intermediate training stage within the self-supervised learning pipeline. By more explicitly modeling the interdependence of these training stages, BiSSL facilitates enhanced information sharing between them, ultimately leading to a backbone parameter initialization that is better suited for the downstream task. We propose a training algorithm that alternates between optimizing the two objectives defined in BiSSL. Using a ResNet-18 backbone pre-trained with SimCLR on the STL10 dataset, we demonstrate that our proposed framework consistently achieves improved or competitive classification accuracies across various downstream image classification datasets compared to the conventional self-supervised learning pipeline. Qualitative analyses of the backbone features further suggest that BiSSL enhances the alignment of downstream features in the backbone prior to fine-tuning.

Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models

Automatic speech recognition (ASR) systems are known to be vulnerable to adversarial attacks. This paper addresses detection and defence against targeted white-box attacks on speech signals for ASR systems. While existing work has utilised diffusion models (DMs) to purify adversarial examples, achieving state-of-the-art results in keyword spotting tasks, their effectiveness for more complex tasks such as sentence-level ASR remains unexplored. Additionally, the impact of the number of forward diffusion steps on performance is not well understood. In this paper, we systematically investigate the use of DMs for defending against adversarial attacks on sentences and examine the effect of varying forward diffusion steps. Through comprehensive experiments on the Mozilla Common Voice dataset, we demonstrate that two forward diffusion steps can completely defend against adversarial attacks on sentences. Moreover, we introduce a novel, training-free approach for detecting adversarial attacks by leveraging a pre-trained DM. Our experimental results show that this method can detect adversarial attacks with high accuracy.

Speaker and Style Disentanglement of Speech Based on Contrastive Predictive Coding Supported Factorized Variational Autoencoder

Speech signals encompass various information across multiple levels including content, speaker, and style. Disentanglement of these information, although challenging, is important for applications such as voice conversion. The contrastive predictive coding supported factorized variational autoencoder achieves unsupervised disentanglement of a speech signal into speaker and content embeddings by assuming speaker info to be temporally more stable than content-induced variations. However, this assumption may introduce other temporal stable information into the speaker embeddings, like environment or emotion, which we call style. In this work, we propose a method to further disentangle non-content features into distinct speaker and style features, notably by leveraging readily accessible and well-defined speaker labels without the necessity for style labels. Experimental results validate the proposed method's effectiveness on extracting disentangled features, thereby facilitating speaker, style, or combined speaker-style conversion.

Audio xLSTMs: Learning Self-Supervised Audio Representations with xLSTMs

While the transformer has emerged as the eminent neural architecture, several independent lines of research have emerged to address its limitations. Recurrent neural approaches have also observed a lot of renewed interest, including the extended long short-term memory (xLSTM) architecture, which reinvigorates the original LSTM architecture. However, while xLSTMs have shown competitive performance compared to the transformer, their viability for learning self-supervised general-purpose audio representations has not yet been evaluated. This work proposes Audio xLSTM (AxLSTM), an approach to learn audio representations from masked spectrogram patches in a self-supervised setting. Pretrained on the AudioSet dataset, the proposed AxLSTM models outperform comparable self-supervised audio spectrogram transformer (SSAST) baselines by up to 20% in relative performance across a set of ten diverse downstream tasks while having up to 45% fewer parameters.

The Effect of Training Dataset Size on Discriminative and Diffusion-Based Speech Enhancement Systems

The performance of deep neural network-based speech enhancement systems typically increases with the training dataset size. However, studies that investigated the effect of training dataset size on speech enhancement performance did not consider recent approaches, such as diffusion-based generative models. Diffusion models are typically trained with massive datasets for image generation tasks, but whether this is also required for speech enhancement is unknown. Moreover, studies that investigated the effect of training dataset size did not control for the data diversity. It is thus unclear whether the performance improvement was due to the increased dataset size or diversity. Therefore, we systematically investigate the effect of training dataset size on the performance of popular state-of-the-art discriminative and diffusion-based speech enhancement systems. We control for the data diversity by using a fixed set of speech utterances, noise segments and binaural room impulse responses to generate datasets of different sizes. We find that the diffusion-based systems do not benefit from increasing the training dataset size as much as the discriminative systems. They perform the best relative to the discriminative systems with datasets of 10 h or less, but they are outperformed by the discriminative systems with datasets of 100 h or more.

Zero-Shot Audio Captioning Using Soft and Hard Prompts

In traditional audio captioning methods, a model is usually trained in a fully supervised manner using a human-annotated dataset containing audio-text pairs and then evaluated on the test sets from the same dataset. Such methods have two limitations. First, these methods are often data-hungry and require time-consuming and expensive human annotations to obtain audio-text pairs. Second, these models often suffer from performance degradation in cross-domain scenarios, i.e., when the input audio comes from a different domain than the training set, which, however, has received little attention. We propose an effective audio captioning method based on the contrastive language-audio pre-training (CLAP) model to address these issues. Our proposed method requires only textual data for training, enabling the model to generate text from the textual feature in the cross-modal semantic space.In the inference stage, the model generates the descriptive text for the given audio from the audio feature by leveraging the audio-text alignment from CLAP.We devise two strategies to mitigate the discrepancy between text and audio embeddings: a mixed-augmentation-based soft prompt and a retrieval-based acoustic-aware hard prompt. These approaches are designed to enhance the generalization performance of our proposed model, facilitating the model to generate captions more robustly and accurately. Extensive experiments on AudioCaps and Clotho benchmarks show the effectiveness of our proposed method, which outperforms other zero-shot audio captioning approaches for in-domain scenarios and outperforms the compared methods for cross-domain scenarios, underscoring the generalization ability of our method.

Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations

Despite its widespread adoption as the prominent neural architecture, the Transformer has spurred several independent lines of work to address its limitations. One such approach is selective state space models, which have demonstrated promising results for language modelling. However, their feasibility for learning self-supervised, general-purpose audio representations is yet to be investigated. This work proposes Audio Mamba, a selective state space model for learning general-purpose audio representations from randomly masked spectrogram patches through self-supervision. Empirical results on ten diverse audio recognition downstream tasks show that the proposed models, pretrained on the AudioSet dataset, consistently outperform comparable self-supervised audio spectrogram transformer (SSAST) baselines by a considerable margin and demonstrate better performance in dataset size, sequence length and model size comparisons.

Noise-Robust Keyword Spotting through Self-supervised Pretraining

Voice assistants are now widely available, and to activate them a keyword spotting (KWS) algorithm is used. Modern KWS systems are mainly trained using supervised learning methods and require a large amount of labelled data to achieve a good performance. Leveraging unlabelled data through self-supervised learning (SSL) has been shown to increase the accuracy in clean conditions. This paper explores how SSL pretraining such as Data2Vec can be used to enhance the robustness of KWS models in noisy conditions, which is under-explored. Models of three different sizes are pretrained using different pretraining approaches and then fine-tuned for KWS. These models are then tested and compared to models trained using two baseline supervised learning methods, one being standard training using clean data and the other one being multi-style training (MTR). The results show that pretraining and fine-tuning on clean data is superior to supervised learning on clean data across all testing conditions, and superior to supervised MTR for testing conditions of SNR above 5 dB. This indicates that pretraining alone can increase the model's robustness. Finally, it is found that using noisy data for pretraining models, especially with the Data2Vec-denoising approach, significantly enhances the robustness of KWS models in noisy conditions.

Neural Networks Hear You Loud And Clear: Hearing Loss Compensation Using Deep Neural Networks

This article investigates the use of deep neural networks (DNNs) for hearing-loss compensation. Hearing loss is a prevalent issue affecting millions of people worldwide, and conventional hearing aids have limitations in providing satisfactory compensation. DNNs have shown remarkable performance in various auditory tasks, including speech recognition, speaker identification, and music classification. In this study, we propose a DNN-based approach for hearing-loss compensation, which is trained on the outputs of hearing-impaired and normal-hearing DNN-based auditory models in response to speech signals. First, we introduce a framework for emulating auditory models using DNNs, focusing on an auditory-nerve model in the auditory pathway. We propose a linearization of the DNN-based approach, which we use to analyze the DNN-based hearing-loss compensation. Additionally we develop a simple approach to choose the acoustic center frequencies of the auditory model used for the compensation strategy. Finally, we evaluate the DNN-based hearing-loss compensation strategies using listening tests with hearing impaired listeners. The results demonstrate that the proposed approach results in feasible hearing-loss compensation strategies. Our proposed approach was shown to provide an increase in speech intelligibility and was found to outperform a conventional approach in terms of perceived speech quality.

How to train your ears: Auditory-model emulation for large-dynamic-range inputs and mild-to-severe hearing losses

Advanced auditory models are useful in designing signal-processing algorithms for hearing-loss compensation or speech enhancement. Such auditory models provide rich and detailed descriptions of the auditory pathway, and might allow for individualization of signal-processing strategies, based on physiological measurements. However, these auditory models are often computationally demanding, requiring significant time to compute. To address this issue, previous studies have explored the use of deep neural networks to emulate auditory models and reduce inference time. While these deep neural networks offer impressive efficiency gains in terms of computational time, they may suffer from uneven emulation performance as a function of auditory-model frequency-channels and input sound pressure level, making them unsuitable for many tasks. In this study, we demonstrate that the conventional machine-learning optimization objective used in existing state-of-the-art methods is the primary source of this limitation. Specifically, the optimization objective fails to account for the frequency- and level-dependencies of the auditory model, caused by a large input dynamic range and different types of hearing losses emulated by the auditory model. To overcome this limitation, we propose a new optimization objective that explicitly embeds the frequency- and level-dependencies of the auditory model. Our results show that this new optimization objective significantly improves the emulation performance of deep neural networks across relevant input sound levels and auditory-model frequency channels, without increasing the computational load during inference. Addressing these limitations is essential for advancing the application of auditory models in signal-processing tasks, ensuring their efficacy in diverse scenarios.