Related papers: Robust Lossy Audio Compression Identification
Speech recognition system performance degrades in noisy environments. If the acoustic models are built using features of clean utterances, the features of a noisy test utterance would be acoustically mismatched with the trained model. This…
Noise robust compressive sensing algorithm is considered. This algorithm allows an efficient signal reconstruction in the presence of different types of noise due to the possibility to change minimization norm. For instance, the commonly…
Error-bounded lossy compression is one of the most effective techniques for scientific data reduction. However, the traditional trial-and-error approach used to configure lossy compressors for finding the optimal trade-off between…
Many industrial applications use Metric Learning as a way to circumvent scalability issues when designing systems with a high number of classes. Because of this, this field of research is attracting a lot of interest from the academic and…
The rise of music large language models (LLMs) demands robust methods of evaluating output quality, especially in distinguishing high-quality compositions from "garbage music". Curiously, we observe that the standard cross-entropy loss -- a…
A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By…
Data representation is crucial for the success of machine learning models. In the context of quantum machine learning with near-term quantum computers, equally important considerations of how to efficiently input (encode) data and…
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…
The need to digitize signals with intricate spectral characteristics often challenges traditional analog-to-digital converters (ADCs). The recently proposed modulo-ADC architecture offers a promising alternative by leveraging inherent…
Standard fine-tuning of pre-trained audio models couples representation learning with classifier training, which can obscure the true quality of the learned representations. In this work, we advocate for a disentangled two-stage framework…
In this paper, techniques for improving multichannel lossless coding are examined. A method is proposed for the simultaneous coding of two or more different renderings (mixes) of the same content. The signal model uses both past samples of…
Most data is automatically collected and only ever "seen" by algorithms. Yet, data compressors preserve perceptual fidelity rather than just the information needed by algorithms performing downstream tasks. In this paper, we characterize…
With the advancement of audio generation, generative models can produce highly realistic audios. However, the proliferation of deepfake general audio can pose negative consequences. Therefore, we propose a new task, deepfake general audio…
Sparse Bayesian learning has promoted many effective frameworks for brain activity decoding, especially for the reconstruction of muscle activity. However, existing sparse Bayesian learning mainly employs Gaussian distribution as error…
It has been reported that deep learning models are extremely vulnerable to small but intentionally chosen perturbations of its input. In particular, a deep network, despite its near-optimal accuracy on the clean images, often mis-classifies…
In recent years, research on learning with noisy labels has focused on devising novel algorithms that can achieve robustness to noisy training labels while generalizing to clean data. These algorithms often incorporate sophisticated…
How to efficiently utilize the temporal features is crucial, yet challenging, for video restoration. The temporal features usually contain various noisy and uncorrelated information, and they may interfere with the restoration of the…
Lossless image compression is an essential research field in image compression. Recently, learning-based image compression methods achieved impressive performance compared with traditional lossless methods, such as WebP, JPEG2000, and FLIF.…
In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate. The increasing demand for visual analysis applications, particularly in classification tasks, has emphasized…
Well-known for its simplicity and effectiveness in classification, AdaBoost, however, suffers from overfitting when class-conditional distributions have significant overlap. Moreover, it is very sensitive to noise that appears in the…