Related papers: FlexiAST: Flexibility is What AST Needs

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 observed a lot of renewed interest, including the extended…

In this work, we investigate the challenging problem of on-demand semantic communication over heterogeneous wireless networks. We propose a fidelity-adjustable semantic transmission framework (FAST) that empowers wireless devices to send…

The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…

Reasoning about spatial audio with large language models requires a spatial audio encoder as an acoustic front-end to obtain audio embeddings for further processing. Such an encoder needs to capture all information required to detect the…

The development of scientific data analyses is a resource-intensive process that often yields results with untapped potential for reuse and reinterpretation. In many cases, a developed analysis can be used to measure more than it was…

Often, the storage and computational constraints of embeddeddevices demand that a single on-device ASR model serve multiple use-cases / domains. In this paper, we propose aFlexibleTransducer(FlexiT) for on-device automatic speech…

Arbitrary style transfer (AST) transfers arbitrary artistic styles onto content images. Despite the recent rapid progress, existing AST methods are either incapable or too slow to run at ultra-resolutions (e.g., 4K) with limited resources,…

A recently proposed analogue transformation method has allowed the extension of transformation acoustics to general spacetime transformations. We analyze here in detail the differences between this new analogue transformation acoustics…

Foundation models achieve state-of-the-art performance across different tasks, but their size and computational demands raise concerns about accessibility and sustainability. Existing efficiency methods often require additional retraining…

The existence of a plethora of language models makes the problem of selecting the best one for a custom task challenging. Most state-of-the-art methods leverage transformer-based models (e.g., BERT) or their variants. Training such models…

Sparsity-aware training is an effective approach for transforming large language models (LLMs) into hardware-friendly sparse patterns, thereby reducing latency and memory consumption during inference. In this paper, we propose Continuous…

Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling objectives. However, convolutional patchification with temporal downsampling lowers the effective…

Recent research has shown that large language models (LLMs) can utilize low-precision floating point (FP) quantization to deliver high efficiency while maintaining original model accuracy. In particular, recent works have shown the…

Respiratory sound classification is hindered by the limited size, high noise levels, and severe class imbalance of benchmark datasets like ICBHI 2017. While Transformer-based models offer powerful feature extraction capabilities, they are…

Transformers and State-Space Models (SSMs) have advanced audio classification by modeling spectrograms as sequences of patches. However, existing models such as the Audio Spectrogram Transformer (AST) and Audio Mamba (AuM) adopt square…

Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific adaptors that modify frozen layer weights or features to…

We present a noise-aware, sensor-specific ensemble approach for robust human activity recognition on the 2nd WEAR Dataset Challenge. Our method leverages the PatchTST transformer architecture, training four independent models-one per…

Parameter-Efficient Fine-Tuning (PEFT) has become a key strategy for adapting large language models, with recent advances in sparse tuning reducing overhead by selectively updating key parameters or subsets of data. Existing approaches…

Vision transformers have excelled in various computer vision tasks but mostly rely on rigid input sampling using a fixed-size grid of patches. It limits their applicability in real-world problems, such as active visual exploration, where…

Recently, more and more personalized speech enhancement systems (PSE) with excellent performance have been proposed. However, two critical issues still limit the performance and generalization ability of the model: 1) Acoustic environment…