Related papers: Aliasing Reduction in Neural Amp Modeling by Smoot…
Neural Radiance Fields (NeRF) have shown remarkable success in representing 3D scenes and generating novel views. However, they often struggle with aliasing artifacts, especially when rendering images from different camera distances from…
We present our experiments in training robust to noise an end-to-end automatic speech recognition (ASR) model using intensive data augmentation. We explore the efficacy of fine-tuning a pre-trained model to improve noise robustness, and we…
Stochastic resonance (SR) could amplify weak electric-field signals in nonlinear systems by means of the externally injected noises. Here we propose and experimentally demonstrate a modified SR method, termed squeezing-induced SR,…
High-resolution simulations often rely on the Adaptive Mesh Resolution (AMR) technique to optimize memory consumption versus attainable precision. While this technique allows for dramatic improvements in terms of computing performance, the…
Next-generation communication and localization systems increasingly rely on extremely large-scale arrays (XL-arrays), which promise unprecedented spatial resolution and new functionalities. These gains arise from their inherent operation in…
Most existing text-to-image person retrieval methods usually assume that the training image-text pairs are perfectly aligned; however, the noisy correspondence(NC) issue (i.e., incorrect or unreliable alignment) exists due to poor image…
Past studies on end-to-end meeting transcription have focused on model architecture and have mostly been evaluated on simulated meeting data. We present a novel study aiming to optimize the use of a Speaker-Attributed ASR (SA-ASR) system in…
Reducing noise interference is crucial for automatic speech recognition (ASR) in a real-world scenario. However, most single-channel speech enhancement (SE) generates "processing artifacts" that negatively affect ASR performance. Hence, in…
Arterial spin labeling (ASL) allows to quantify the cerebral blood flow (CBF) by magnetic labeling of the arterial blood water. ASL is increasingly used in clinical studies due to its noninvasiveness, repeatability and benefits in…
End-to-end (E2E) multi-channel ASR systems show state-of-the-art performance in far-field ASR tasks by joint training of a multi-channel front-end along with the ASR model. The main limitation of such systems is that they are usually…
Deep learning models achieve strong performance in chest radiograph (CXR) interpretation, yet fairness and reliability concerns persist. Models often show uneven accuracy across patient subgroups, leading to hidden failures not reflected in…
Speech models are often trained on sensitive data in order to improve model performance, leading to potential privacy leakage. Our work considers noise masking attacks, introduced by Amid et al. 2022, which attack automatic speech…
Automatic speech recognition (ASR) models trained on large amounts of audio data are now widely used to convert speech to written text in a variety of applications from video captioning to automated assistants used in healthcare and other…
The performance of automatic speech recognition systems under noisy environments still leaves room for improvement. Speech enhancement or feature enhancement techniques for increasing noise robustness of these systems usually add components…
The transcriptions used to train an Automatic Speech Recognition (ASR) system may contain errors. Usually, either a quality control stage discards transcriptions with too many errors, or the noisy transcriptions are used as is. We introduce…
The signal to noise ratio (SNR) is one of the important measures for reducing the noise.A technique that uses a linear prediction error filter (LPEF) and an adaptive digital filter (ADF) to achieve noise reduction in a speech and image…
Automatic speech recognition (ASR) outcomes serve as input for downstream tasks, substantially impacting the satisfaction level of end-users. Hence, the diagnosis and enhancement of the vulnerabilities present in the ASR model bear…
In recent years, significant progress has been made in deep model-based automatic speech recognition (ASR), leading to its widespread deployment in the real world. At the same time, adversarial attacks against deep ASR systems are highly…
Pre-trained automatic speech recognition (ASR) models have demonstrated strong performance on a variety of tasks. However, their performance can degrade substantially when the input audio comes from different recording channels. While…
It is well-known that neural networks can unintentionally memorize their training examples, causing privacy concerns. However, auditing memorization in large non-auto-regressive automatic speech recognition (ASR) models has been challenging…