Tootfinder

Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes
Rogier C. van Dalen, Shucong Zhang, Titouan Parcollet, Sourav Bhattacharya
https://arxiv.org/abs/2506.10653

Robust Unsupervised Adaptation of a Speech Recogniser Using Entropy Minimisation and Speaker Codes
Speech recognisers usually perform optimally only in a specific environment and need to be adapted to work well in another. For adaptation to a new speaker, there is often too little data for fine-tuning to be robust, and that data is usually unlabelled. This paper proposes a combination of approaches to make adaptation to a single minute of data robust. First, instead of estimating the adaptation parameters with cross-entropy on a single error-prone hypothesis or "pseudo-label", this paper pro…

Featureless Wireless Communications using Enhanced Autoencoder
Ruhui Zhang, Wei Lin, Binbin Chen
https://arxiv.org/abs/2507.07474 https://

Featureless Wireless Communications using Enhanced Autoencoder
Artificial intelligence (AI) techniques, particularly autoencoders (AEs), have gained significant attention in wireless communication systems. This paper investigates using an AE to generate featureless signals with a low probability of detection and interception (LPD/LPI). Firstly, we introduce a novel loss function that adds a KL divergence term to the categorical cross entropy, enhancing the noise like characteristics of AE-generated signals while preserving block error rate (BLER). Secondly…

A note on entropy of matter in presence of gravity: status of extensivity of entropy
Saurav Samanta, Bibhas Ranjan Majhi
https://arxiv.org/abs/2507.14817 h…

A note on entropy of matter in presence of gravity: status of extensivity of entropy
Entropy of matter in a very strong gravity depends on cross-sectional area of the container of the system -- is being further bolstered by calculating entropy of a monoatomic gas kept under uniform strong gravity at Newtonian scale. This bypasses the earlier analysis where existence of horizon is crucial. Also the extensivity of this entropy has been discussed in the light of the same of a two-space dimensional ultra-relativistic non-interacting gas without gravity. The whole analysis, as far a…

Single-cell metabolic flux analysis reveals coexisting optimal sub-groups, cross-feeding, and mixotrophy in a cyanobacterial population
Ari\'an Ferrero-Fern\'andez, Paula Prondzinsky, Lucia Gastoldi, David A. Fike, Harrison B. Smith, Daniele De Martino, Andrea De Martino, Shawn Erin McGlynn
https://arxiv.org/abs/2506.059…

Single-cell metabolic flux analysis reveals coexisting optimal sub-groups, cross-feeding, and mixotrophy in a cyanobacterial population
We derive a single-cell level understanding of metabolism in an isogenic cyanobacterial population by integrating secondary ion mass spectrometry (SIMS) derived multi-isotope uptake measurements of Synechocystis sp. PCC6803 with a statistical inference protocol based on Liebig's law of the minimum, the maximum entropy principle, and constraint-based modeling. We find the population is structured in two metabolically distinct clusters: cells optimizing carbon yield while excessively turning over…

Magnetoelectric coupling and its impact on the multicaloric effect
Kentaro Ino, Keisuke Matsuura, Tetsuya Nomoto, Takashi Kurumaji, Yoshinori Tokura, Fumitaka Kagawa
https://arxiv.org/abs/2507.19126

Magnetoelectric coupling and its impact on the multicaloric effect
The multicaloric effect, which represents the reversible entropy change that occurs when both external magnetic and electric fields are applied, is an interesting phenomenon characteristic to multiferroics. Targeting the multicaloric effect in the typical multiferroic (Fe$_{0.95}$Zn$_{0.05}$)$_2$Mo$_3$O$_8$, we experimentally evaluate the isothermal entropy change due to a magnetoelectric cross-correlation. A pronounced cross-correlation-derived isothermal entropy change is found at the magneti…

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/5]:
- Bregman Centroid Guided Cross-Entropy Method
Yuliang Gu, Hongpeng Cao, Marco Caccamo, Naira Hovakimyan

Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning
Le Xu, Chenxing Li, Yong Ren, Yujie Chen, Yu Gu, Ruibo Fu, Shan Yang, Dong Yu
https://arxiv.org/abs/2505.22045

Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning
Current vision-guided audio captioning systems frequently fail to address audiovisual misalignment in real-world scenarios, such as dubbed content or off-screen sounds. To bridge this critical gap, we present an entropy-aware gated fusion framework that dynamically modulates visual information flow through cross-modal uncertainty quantification. Our novel approach employs attention entropy analysis in cross-attention layers to automatically identify and suppress misleading visual cues during mo…

Advancing Lung Disease Diagnosis in 3D CT Scans
Qingqiu Li, Runtian Yuan, Junlin Hou, Jilan Xu, Yuejie Zhang, Rui Feng, Hao Chen
https://arxiv.org/abs/2507.00993

Advancing Lung Disease Diagnosis in 3D CT Scans
To enable more accurate diagnosis of lung disease in chest CT scans, we propose a straightforward yet effective model. Firstly, we analyze the characteristics of 3D CT scans and remove non-lung regions, which helps the model focus on lesion-related areas and reduces computational cost. We adopt ResNeSt50 as a strong feature extractor, and use a weighted cross-entropy loss to mitigate class imbalance, especially for the underrepresented squamous cell carcinoma category. Our model achieves a Macr…

Multipartite Markov Gaps and Entanglement Wedge Multiway Cuts
Norihiro Iizuka, Akihiro Miyata, Mitsuhiro Nishida
https://arxiv.org/abs/2507.15262 https://

Multipartite Markov Gaps and Entanglement Wedge Multiway Cuts
The Markov gap, defined as the difference between reflected entropy and mutual information, serves as a diagnostic for quantum recoverability and multipartite entanglement. In holographic settings, it admits a geometric interpretation as the deviation between entanglement wedge cross-sections and RT surfaces. Motivated by this holographic perspective, we propose a generalization of the Markov gap to multipartite systems by using a reflected multi-entropy. The resulting Multipartite Markov gap c…

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss
Yunrui Yu, Hang Su, Cheng-zhong Xu, Zhizhong Su, Jun Zhu
https://arxiv.org/abs/2507.22428

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss
Gradient-based adversarial attacks using the Cross-Entropy (CE) loss often suffer from overestimation due to relative errors in gradient computation induced by floating-point arithmetic. This paper provides a rigorous theoretical analysis of these errors, conducting the first comprehensive study of floating-point computation errors in gradient-based attacks across four distinct scenarios: (i) unsuccessful untargeted attacks, (ii) successful untargeted attacks, (iii) unsuccessful targeted attack…

Pixel-wise Modulated Dice Loss for Medical Image Segmentation
Seyed Mohsen Hosseini
https://arxiv.org/abs/2506.15744 https://arxiv.or…

Pixel-wise Modulated Dice Loss for Medical Image Segmentation
Class imbalance and the difficulty imbalance are the two types of data imbalance that affect the performance of neural networks in medical segmentation tasks. In class imbalance the loss is dominated by the majority classes and in difficulty imbalance the loss is dominated by easy to classify pixels. This leads to an ineffective training. Dice loss, which is based on a geometrical metric, is very effective in addressing the class imbalance compared to the cross entropy (CE) loss, which is adopt…

Low-resource keyword spotting using contrastively trained transformer acoustic word embeddings
Julian Herreilers, Christiaan Jacobs, Thomas Niesler
https://arxiv.org/abs/2506.17690

Low-resource keyword spotting using contrastively trained transformer acoustic word embeddings
We introduce a new approach, the ContrastiveTransformer, that produces acoustic word embeddings (AWEs) for the purpose of very low-resource keyword spotting. The ContrastiveTransformer, an encoder-only model, directly optimises the embedding space using normalised temperature-scaled cross entropy (NT-Xent) loss. We use this model to perform keyword spotting for radio broadcasts in Luganda and Bambara, the latter a severely under-resourced language. We compare our model to various existing AWE a…