English
Related papers

Related papers: Adaptive Test-Time Scaling for Zero-Shot Respirato…

200 papers

Due to the scarcity of annotated data and the substantial computational costs of model, conventional tuning methods in medical image segmentation face critical challenges. Current approaches to adapting pretrained models, including…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Chenlin Xu , Lei Zhang , Lituan Wang , Xinyu Pu , Pengfei Ma , Guangwu Qian , Zizhou Wang , Yan Wang

With 4.5 million hours of English speech from 10 different sources across 120 countries and models of up to 10 billion parameters, we explore the frontiers of scale for automatic speech recognition. We propose data selection techniques to…

Computation and Language · Computer Science 2021-11-30 Alex Xiao , Weiyi Zheng , Gil Keren , Duc Le , Frank Zhang , Christian Fuegen , Ozlem Kalinli , Yatharth Saraf , Abdelrahman Mohamed

In this paper, a modification to the training process of the popular SPLICE algorithm has been proposed for noise robust speech recognition. The modification is based on feature correlations, and enables this stereo-based algorithm to…

Machine Learning · Computer Science 2014-02-12 D. S. Pavan Kumar , N. Vishnu Prasad , Vikas Joshi , S. Umesh

Text and vision foundation models can perform many tasks in a zero-shot setting, a desirable property that enables these systems to be applied in general and low-resource settings. There has been far less work, however, on the zero-shot…

Computation and Language · Computer Science 2024-03-29 Rao Ma , Adian Liusie , Mark J. F. Gales , Kate M. Knill

Test-time scaling has emerged as a transformative paradigm for enhancing the performance of large reasoning models, enabling dynamic allocation of computational resources during inference. However, as the landscape of reasoning models…

Artificial Intelligence · Computer Science 2025-10-08 Zhangyue Yin , Qiushi Sun , Zhiyuan Zeng , Zhiyuan Yu , Qipeng Guo , Xuanjing Huang , Xipeng Qiu

Contrastive Language-Audio Pretraining (CLAP) is pre-trained to associate audio features with human language, making it a natural zero-shot classifier to recognize unseen sound categories. To adapt CLAP to downstream tasks, prior works…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-18 Yiming Li , Xiangdong Wang , Hong Liu

This paper presents a novel zero-shot learning approach towards personalized speech enhancement through the use of a sparsely active ensemble model. Optimizing speech denoising systems towards a particular test-time speaker can improve…

Audio and Speech Processing · Electrical Eng. & Systems 2021-05-11 Aswin Sivaraman , Minje Kim

The audio spectrogram is a time-frequency representation that has been widely used for audio classification. One of the key attributes of the audio spectrogram is the temporal resolution, which depends on the hop size used in the Short-Time…

Sound · Computer Science 2024-01-15 Haohe Liu , Xubo Liu , Qiuqiang Kong , Wenwu Wang , Mark D. Plumbley

Recently, Automatic Speech Recognition (ASR) systems (e.g., Whisper) have achieved remarkable accuracy improvements but remain highly sensitive to real-world unseen data (data with large distribution shifts), including noisy environments…

Sound · Computer Science 2026-03-06 Linghan Fang , Tianxin Xie , Li Liu

Zero-shot depth completion has gained attention for its ability to generalize across environments without sensor-specific datasets or retraining. However, most existing approaches rely on diffusion-based test-time optimization, which is…

Computer Vision and Pattern Recognition · Computer Science 2026-04-06 Minseok Seo , Wonjun Lee , Jaehyuk Jang , Changick Kim

Although numerous recent studies have suggested new frameworks for zero-shot TTS using large-scale, real-world data, studies that focus on the intelligibility of zero-shot TTS are relatively scarce. Zero-shot TTS demands additional efforts…

Audio and Speech Processing · Electrical Eng. & Systems 2024-01-31 Sunghee Jung , Won Jang , Jaesam Yoon , Bongwan Kim

Large reasoning models (LRMs) have shown significant progress in test-time scaling through chain-of-thought prompting. Current approaches like search-o1 integrate retrieval augmented generation (RAG) into multi-step reasoning processes but…

Computation and Language · Computer Science 2026-01-21 Kaiwen Wei , Rui Shan , Dongsheng Zou , Jianzhong Yang , Bi Zhao , Junnan Zhu , Jiang Zhong

Training-free guidance enables controlled generation in diffusion and flow models, but most methods rely on gradients and assume differentiable objectives. This work focuses on training-free guidance addressing challenges from…

Machine Learning · Computer Science 2025-06-12 Yingqing Guo , Yukang Yang , Hui Yuan , Mengdi Wang

Recent advances in stereo matching have focused on accuracy, often at the cost of significantly increased model size. Traditionally, the community has regarded efficient models as incapable of zero-shot ability due to their limited…

Computer Vision and Pattern Recognition · Computer Science 2026-04-16 Junpeng Jing , Weixun Luo , Ye Mao , Krystian Mikolajczyk

Audio-text models trained via contrastive learning offer a practical approach to perform audio classification through natural language prompts, such as "this is a sound of" followed by category names. In this work, we explore alternative…

Sound · Computer Science 2024-09-23 Michel Olvera , Paraskevas Stamatiadis , Slim Essid

Medical time series analysis is challenging due to data sparsity, noise, and highly variable recording lengths. Prior work has shown that stochastic sparse sampling effectively handles variable-length signals, while retrieval-augmented…

Machine Learning · Computer Science 2025-10-06 Aydin Javadov , Samir Garibov , Tobias Hoesli , Qiyang Sun , Florian von Wangenheim , Joseph Ollier , Björn W. Schuller

Test-time adaptation (TTA) of visual language models has recently attracted significant attention as a solution to the performance degradation caused by distribution shifts in downstream tasks. However, existing cache-based TTA methods have…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Haotian Zhai , Xinyu Chen , Can Zhang , Tianming Sha , Ruirui Li

A new paradigm to estimate the gradient of a black-box scalar function is introduced, considering it as a member of a set of admissible gradients that are computed using existing function samples. Results on gradient estimate accuracy,…

Optimization and Control · Mathematics 2025-08-28 Lorenzo Sabug , Fredy Ruiz , Lorenzo Fagiano

We presented the Treff adapter, a training-efficient adapter for CLAP, to boost zero-shot classification performance by making use of a small set of labelled data. Specifically, we designed CALM to retrieve the probability distribution of…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-30 Jinhua Liang , Xubo Liu , Haohe Liu , Huy Phan , Emmanouil Benetos , Mark D. Plumbley , Wenwu Wang

Contextual automatic speech recognition (ASR) systems allow for recognizing out-of-vocabulary (OOV) words, such as named entities or rare words. However, it remains challenging due to limited training data and ambiguous or inconsistent…

Computation and Language · Computer Science 2025-09-03 Changsong Liu , Yizhou Peng , Eng Siong Chng