20 results for “Lombard effect”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
A text-to-speech model is trained to simulate the Lombard effect, improving clarity in noisy conditions.
This paper studies the effect of graph neighbors on forecasting accuracy in spatio-temporal graph neural networks.
This paper compares and contrasts variants of targeted maximum likelihood estimation (TMLE) and augmented inverse-probability weighting (AIPW) with machine-learning nuisance models.
This paper introduces a new method, S-GBT, to improve the robustness of NLP models against word substitution attacks by controlling both first and second order sensitivity.
This paper investigates the impact of heterogeneous peers on revision behavior in large language models.
This paper investigates the effect of input diversity on the transferability of adversarial attacks and finds that it can be beneficial for standard surrogates but harmful for robust ones.
Nanqing Luo, Xusheng Li, Haizhou Wang, Shuangyi Zhu +2 more
The paper introduces a novel record-and-replay detection mechanism to accurately detect the true avalanche effect in ransomware, achieving high accuracy against real-world samples.
This paper introduces a Gaussian approximation for the finite-sample distribution of ridge regression estimator, allowing for heteroskedasticity and autocorrelation in the data generating process. Two…
This paper presents a double machine learning procedure for estimating the target risk of an arbitrary black-box prediction model under a general loss function.
The scaling exponent in neural scaling laws is not fixed but systematically depends on the optimizer used, with preconditioned optimizers generally yielding steeper scaling.
This paper measures and analyzes the overuse of epanorthosis, a rhetorical figure, in large language models and proposes techniques to mitigate it.
Cande Lian, Wentao Zeng, Jiabin Wu, Yiming Bie +1 more
This paper develops FGDSE, a feature-governed dynamic stacking ensemble for climate-resilient charging-asset management in electric vehicles, which predicts daily fault risk over a multi-week horizon…
This paper tests how learned context affects logical judgments in AI models by introducing soft prefixes to syllogistic reasoning benchmarks and studies their impact.
This paper investigates neural activity during five auditory conditions using EEG recordings from a 5-year-old participant, revealing condition-specific modulation of neural oscillatory activity and d…
The paper introduces Outstrumental Variable Regression (OVR) to estimate causal effects from observational data by exploiting variation in the outcome mechanism across environments.
The paper empirically analyzes the impact of cross-chain interoperability on DeFi lending protocols, finding that bridge volume significantly affects performance but that increased integrations can si…
A framework is proposed to measure the defensive performance of football players through their positional behavior.