Related papers: HydraFormer: One Encoder For All Subsampling Rates

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes…

Subcortical segmentation remains challenging despite its important applications in quantitative structural analysis of brain MRI scans. The most accurate method, manual segmentation, is highly labor intensive, so automated tools like…

Deepfake speech detection presents a growing challenge as generative audio technologies continue to advance. We propose a hybrid training framework that advances detection performance through novel augmentation strategies. First, we…

Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…

Low-resource accented speech recognition is one of the important challenges faced by current ASR technology in practical applications. In this study, we propose a Conformer-based architecture, called Aformer, to leverage both the acoustic…

Current semantic segmentation models have achieved great success under the independent and identically distributed (i.i.d.) condition. However, in real-world applications, test data might come from a different domain than training data.…

Transformer models rely on self-attention to capture token dependencies but face challenges in effectively integrating positional information while allowing multi-head attention (MHA) flexibility. Prior methods often model semantic and…

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…

Transformer-based pre-trained language models are vocabulary-dependent, mapping by default each token to its corresponding embedding. This one-to-one mapping results into embedding matrices that occupy a lot of memory (i.e. millions of…

Formants are the spectral maxima that result from acoustic resonances of the human vocal tract, and their accurate estimation is among the most fundamental speech processing problems. Recent work has been shown that those frequencies can…

There is a growing trend to outsource the inference task of large transformer models to cloud servers. However, this poses a severe threat to users' private data as they are exposed to cloud servers after uploading. Although several works…

Convolutional neural networks (CNNs) have been the consensus for medical image segmentation tasks. However, they suffer from the limitation in modeling long-range dependencies and spatial correlations due to the nature of convolution…

Transformer-based self-supervised models have achieved remarkable success in speech processing, but their large size and high inference cost present significant challenges for real-world deployment. While numerous compression techniques…

Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acoustic information as possible. However, in some models…

Automatic speech recognition research focuses on training and evaluating on static datasets. Yet, as speech models are increasingly deployed on personal devices, such models encounter user-specific distributional shifts. To simulate this…

The task of radio map estimation aims to generate a dense representation of electromagnetic spectrum quantities, such as the received signal strength at each grid point within a geographic region, based on measurements from a subset of…

Hyperspectral image (HSI) classification (HSIC) requires effective modeling of complex spatial-spectral dependencies under limited labeled data and high dimensionality. While transformer-based models have shown strong capability in…

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass…

Most recent scribble-supervised segmentation methods commonly adopt a CNN framework with an encoder-decoder architecture. Despite its multiple benefits, this framework generally can only capture small-range feature dependency for the…

We introduce SPAFormer, an innovative model designed to overcome the combinatorial explosion challenge in the 3D Part Assembly (3D-PA) task. This task requires accurate prediction of each part's poses in sequential steps. As the number of…