English
Related papers

Related papers: FlexiAST: Flexibility is What AST Needs

200 papers

While Large Language Models and their underlying Transformer architecture are remarkably efficient, they do not reflect how our brain processes and learns a diversity of cognitive tasks such as language, nor how it leverages working memory.…

Machine Learning · Computer Science 2026-02-09 Yannis Bendi-Ouis , Xavier Hinaut

Previous work has shown that for low-resource source languages, automatic speech-to-text translation (AST) can be improved by pretraining an end-to-end model on automatic speech recognition (ASR) data from a high-resource language. However,…

Computation and Language · Computer Science 2020-02-11 Mihaela C. Stoian , Sameer Bansal , Sharon Goldwater

Separating target speech from mixed signals containing flexible speaker quantities presents a challenging task. While existing methods demonstrate strong separation performance and noise robustness, they predominantly assume prior knowledge…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-18 Daning Zhang , Ying Wei

Recently, foundation models based on Vision Transformers (ViTs) have become widely available. However, their fine-tuning process is highly resource-intensive, and it hinders their adoption in several edge or low-energy applications. To this…

Computer Vision and Pattern Recognition · Computer Science 2024-08-19 Alessio Devoto , Federico Alvetreti , Jary Pomponi , Paolo Di Lorenzo , Pasquale Minervini , Simone Scardapane

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…

The performance of transformers for time-series forecasting has improved significantly. Recent architectures learn complex temporal patterns by segmenting a time-series into patches and using the patches as tokens. The patch size controls…

Machine Learning · Computer Science 2024-03-25 Yitian Zhang , Liheng Ma , Soumyasundar Pal , Yingxue Zhang , Mark Coates

Despite recent advances, developing general-purpose universal denoising and artifact-removal networks remains largely an open problem: Given fixed network weights, one inherently trades-off specialization at one task (e.g.,~removing Poisson…

Computer Vision and Pattern Recognition · Computer Science 2024-11-19 Kevin Zhang , Sakshum Kulshrestha , Christopher Metzler

We consider a variable metric and inexact version of the FISTA-type algorithm considered in (Chambolle, Pock, 2016, Calatroni, Chambolle, 2019) for the minimization of the sum of two (possibly strongly) convex functions. The proposed…

Optimization and Control · Mathematics 2021-01-12 Simone Rebegoldi , Luca Calatroni

The rapid advancement of generative artificial intelligence has spurred innovative approaches to semantic communication, giving rise to a new paradigm known as generative semantic communication (GSC). The integration of flexible cross-modal…

Signal Processing · Electrical Eng. & Systems 2025-11-03 Yiru Wang , Wanting Yang , Fangli Mou , Zehui Xiong , Zide Fan , Shiwen Mao , Tony Q. S. Quek

Contemporary machine learning models, including large language models, exhibit remarkable capabilities in static tasks yet falter in non-stationary environments due to rigid architectures that hinder continual adaptation and lifelong…

Machine Learning · Computer Science 2026-05-15 Akbar Anbar Jafari , Cagri Ozcinar , Gholamreza Anbarjafari

Recent advances in AI-generated voices have intensified the challenge of detecting deepfake audio, posing risks for scams and the spread of disinformation. To tackle this issue, we establish the largest public voice dataset to date, named…

Feature representations derived from models pre-trained on large-scale datasets have shown their generalizability on a variety of audio analysis tasks. Despite this generalizability, however, task-specific features can outperform if…

Audio and Speech Processing · Electrical Eng. & Systems 2022-06-13 Yun-Ning Hung , Alexander Lerch

LLM-powered conversational assistants are often deployed in a one-size-fits-all manner, which fails to accommodate individual user preferences. Recently, LLM personalization -- tailoring models to align with specific user preferences -- has…

Computation and Language · Computer Science 2025-08-07 Thibaut Thonet , Germán Kruszewski , Jos Rozen , Pierre Erbacher , Marc Dymetman

General-purpose embedding is highly desirable for few-shot even zero-shot learning in many application scenarios, including audio tasks. In order to understand representations better, we conducted a thorough error analysis and visualization…

Sound · Computer Science 2023-03-08 Ankit Shah , Shuyi Chen , Kejun Zhou , Yue Chen , Bhiksha Raj

In recent years, researchers combine both audio and video signals to deal with challenges where actions are not well represented or captured by visual cues. However, how to effectively leverage the two modalities is still under development.…

Computer Vision and Pattern Recognition · Computer Science 2024-01-09 Wentao Zhu

In end-to-end speech translation, acoustic representations learned by the encoder are usually fixed and static, from the perspective of the decoder, which is not desirable for dealing with the cross-modal and cross-lingual challenge in…

Computation and Language · Computer Science 2025-03-19 Wuwei Huang , Dexin Wang , Deyi Xiong

The Short-Time Fourier Transform (STFT) has been a staple of signal processing, often being the first step for many audio tasks. A very familiar process when using the STFT is the search for the best STFT parameters, as they often have…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-17 An Zhao , Krishna Subramani , Paris Smaragdis

Most audio processing pipelines involve transformations that act on fixed-dimensional input representations of audio. For example, when using the Short Time Fourier Transform (STFT) the DFT size specifies a fixed dimension for the input…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-28 Krishna Subramani , Paris Smaragdis

Although Vision Transformers (ViTs) have recently advanced computer vision tasks significantly, an important real-world problem was overlooked: adapting to variable input resolutions. Typically, images are resized to a fixed resolution,…

Computer Vision and Pattern Recognition · Computer Science 2024-05-29 Wenzhuo Liu , Fei Zhu , Shijie Ma , Cheng-Lin Liu

Audio fingerprinting (AFP) allows the identification of unknown audio content by extracting compact representations, termed audio fingerprints, that are designed to remain robust against common audio degradations. Neural AFP methods often…