相关论文: Physics-Informed Transfer Learning for Data-Driven…

Sound source localization (SSL) technology plays a crucial role in various application areas such as fault diagnosis, speech separation, and vibration noise reduction. Although beamforming algorithms are widely used in SSL, their resolution…

Electromagnetic field reconstruction is crucial in many applications, including antenna diagnostics, electromagnetic interference analysis, and system modeling. This paper presents a deep learning-based approach for Far-Field to Near-Field…

Photoacoustic tomography (PAT) is a medical imaging modality that can provide high-resolution tissue images based on the optical absorption. Classical reconstruction methods for quantifying the absorption coefficients rely on sufficient…

Fault diagnosis of rotating machinery plays a important role for the safety and stability of modern industrial systems. However, there is a distribution discrepancy between training data and data of real-world operation scenarios, which…

In this paper, we propose a deep learning based system for the task of deepfake audio detection. In particular, the draw input audio is first transformed into various spectrograms using three transformation methods of Short-time Fourier…

Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods help mitigate this by offering controllable improvements in…

In this paper, we propose a method to adapt a pre-trained deep-learning-based model for underwater acoustic localization to a new environment. We use unsupervised domain adaptation to improve the generalization performance of the model,…

Learning physics-constrained inverse operators-rather than post-processing physics-based reconstructions-is a broadly applicable strategy for problems with expensive forward models. We demonstrate this principle in three-dimensional…

With the development of computer -systems that can collect and analyze enormous volumes of data, the medical profession is establishing several non-invasive tools. This work attempts to develop a non-invasive technique for identifying…

Transfer learning aims to reduce the amount of data required to excel at a new task by re-using the knowledge acquired from learning other related tasks. This paper proposes a novel transfer learning scenario, which distills robust phonetic…

Machine-learning models in high-energy physics are often trained on simulated data, where fully simulated samples are computationally expensive while fast simulation provides large statistics at reduced realism. In this work, we…

Device-guided music transfer adapts playback across unseen devices for users who lack them. Existing methods mainly focus on modifying the timbre, rhythm, harmony, or instrumentation to mimic genres or artists, overlooking the diverse…

Drawing inspiration from the hierarchical processing of the human auditory system, which transforms sound from low-level acoustic features to high-level semantic understanding, we introduce a novel coarse-to-fine audio reconstruction…

We consider the acoustic source imaging problems using multiple frequency data. Using the data of one observation direction/point, we prove that some information (size and location) of the source support can be recovered. A non-iterative…

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up…

Parameter-efficient transfer learning (PETL) methods have emerged as a solid alternative to the standard full fine-tuning approach. They only train a few extra parameters for each downstream task, without sacrificing performance and…

Deep neural network (DNN)-based models for environmental sound classification are not robust against a domain to which training data do not belong, that is, out-of-distribution or unseen data. To utilize pretrained models for the unseen…

Transfer learning is critical for efficient information transfer across multiple related learning problems. A simple, yet effective transfer learning approach utilizes deep neural networks trained on a large-scale task for feature…

Supervised deep learning methods for performing audio source separation can be very effective in domains where there is a large amount of training data. While some music domains have enough data suitable for training a separation system,…

Recently, the pre-trained Transformer models have received a rising interest in the field of speech processing thanks to their great success in various downstream tasks. However, most fine-tuning approaches update all the parameters of the…