Tootfinder

Messrs. Dunning and Kruger agree with me on this yahoo:
Trump official rebuked for declaring that a ‘benevolent monarchy’ is best for Middle East - Raw Story
https://www.rawstory.com/tom-barrack-2674380626/

Love the impartial both-sided-ism of "even though the shutdown is the result of both Republicans and Democrats refusing to agree to a deal."
Who has refused to call the House back in session? Who has said "Don't negotiate"? Who has refused to fund #SNAP?

Love the impartial both-sided-ism of "even though the shutdown is the result of both Republicans and Democrats refusing to agree to a deal."
Who has refused to call the House back in session? Who has said "Don't negotiate"? Who has refused to fund #SNAP?

Olha. Parece que vai vir aí mais uma vagazinha de refugiados, agora do Bluesky. Preparem-se.

Eigentlich ist es egal, ob da jetzt "adults only" dran steht oder einfach ein normales Restaurant in der Deutschschweiz betreten wird. Mit Kindern kommt man sich immer als Störfaktor vor. Egal wie gut sich diese benehmen.
War aber früher™ in meiner Erinnerung auch nicht wirklich anders. Ausser im Mövi (und ganz wenigen anderen Ausnahmen) war man in der Deutschschweiz als Kind nie wirklich willkommen. Ins Mövi zu gehen hab ich aber geliebt.
https://www.watson.ch/schweiz/interview/319042788-schweizer-restaurants-sperren-kinder-aus-das-steckt-hinter-dem-trend

Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASR
Ling Sun, Charlotte Zhu, Shuju Shi
https://arxiv.org/abs/2510.10738 https://arxiv.org/…

Proficiency-Aware Adaptation and Data Augmentation for Robust L2 ASR
General-purpose ASR underperforms for atypical speakers, such as L2 learners, reinforcing bias and limiting use in education and accessibility. Using the CEFR-graded Speak and Improve corpus, we show that naive fine-tuning of Whisper reduces average WER but simultaneously widens disparities and disproportionately harms lower-level learners. To address this, we propose two strategies: (i) proficiency-aware multitask learning, jointly optimizing ASR with proficiency classification, and (ii) targe…

DeepTrust: Multi-Step Classification through Dissimilar Adversarial Representations for Robust Android Malware Detection
Daniel Pulido-Cort\'azar, Daniel Gibert, Felip Many\`a
https://arxiv.org/abs/2510.12310

DeepTrust: Multi-Step Classification through Dissimilar Adversarial Representations for Robust Android Malware Detection
Over the last decade, machine learning has been extensively applied to identify malicious Android applications. However, such approaches remain vulnerable against adversarial examples, i.e., examples that are subtly manipulated to fool a machine learning model into making incorrect predictions. This research presents DeepTrust, a novel metaheuristic that arranges flexible classifiers, like deep neural networks, into an ordered sequence where the final decision is made by a single internal model…

Articulation-Informed ASR: Integrating Articulatory Features into ASR via Auxiliary Speech Inversion and Cross-Attention Fusion
Ahmed Adel Attia, Jing Liu, Carol Espy Wilson
https://arxiv.org/abs/2510.08585

Articulation-Informed ASR: Integrating Articulatory Features into ASR via Auxiliary Speech Inversion and Cross-Attention Fusion
Prior works have investigated the use of articulatory features as complementary representations for automatic speech recognition (ASR), but their use was largely confined to shallow acoustic models. In this work, we revisit articulatory information in the era of deep learning and propose a framework that leverages articulatory representations both as an auxiliary task and as a pseudo-input to the recognition model. Specifically, we employ speech inversion as an auxiliary prediction task, and th…

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/4]:
- DeepTrust: Multi-Step Classification through Dissimilar Adversarial Representations for Robust An...
Daniel Pulido-Cort\'azar, Daniel Gibert, Felip Many\`a

Dual Data Scaling for Robust Two-Stage User-Defined Keyword Spotting
Zhiqi Ai, Han Cheng, Yuxin Wang, Shiyi Mu, Shugong Xu, Yongjin Zhou
https://arxiv.org/abs/2510.10740 https:/…

Dual Data Scaling for Robust Two-Stage User-Defined Keyword Spotting
In this paper, we propose DS-KWS, a two-stage framework for robust user-defined keyword spotting. It combines a CTC-based method with a streaming phoneme search module to locate candidate segments, followed by a QbyT-based method with a phoneme matcher module for verification at both the phoneme and utterance levels. To further improve performance, we introduce a dual data scaling strategy: (1) expanding the ASR corpus from 460 to 1,460 hours to strengthen the acoustic model; and (2) leveraging…