arXiv subjects

Sarah Robinson

Publications and source records attributed to Sarah Robinson.

4 recordsLinked to original sources

arXiv2025

"What do you expect? You're part of the internet": Analyzing Celebrities' Experiences as Usees of Deepfake Technology

Deepfake technology is often used to create non-consensual synthetic intimate imagery (NSII), mainly of celebrity women. Through Critical Discursive Psychological analysis we ask; i) how celebrities construct being targeted by deepfakes and ii) how they navigate infrastructural and social obstacles when seeking recourse. In this paper, we adopt Baumers concept of Usees (stakeholders who are non-consenting, unaware and directly targeted by technology), to understand public statements made by eight celebrity women and one non-binary individual targeted with NSII. Celebrities describe harms of being non-consensually targeted by deepfakes and the distress of becoming aware of these videos. They describe various infrastructural/social factors (e.g. blaming/ silencing narratives and the industry behind deepfake abuse) which hinder activism and recourse. This work has implications in recognizing the roles of various stakeholders in the infrastructures underlying deepfake abuse and the potential of human-computer interaction to improve existing recourses for NSII. We also contribute to understanding how false beliefs online facilitate deepfake abuse. Future work should involve interventions which challenge the values and false beliefs which motivate NSII creation/dissemination.

cs.HC↗

arXiv2025

Self-Supervised Speech Quality Assessment (S3QA): Leveraging Speech Foundation Models for a Scalable Speech Quality Metric

Methods for automatically assessing speech quality in real world environments are critical for developing robust human language technologies and assistive devices. Behavioral ratings provided by human raters (e.g., mean opinion scores; MOS) are considered the gold standard, but they are susceptible to variability between individual raters, cannot easily be generalized across corpora, and are labor-intensive to collect, thus limiting the acoustic challenges they can quantify. Here, we present a new, scalable method for automatically assessing speech quality: the self-supervised speech quality assessment (S3QA) model. First, we manipulated high quality utterances from multiple speech corpora, using a wide range of acoustic challenges intended to emulate common sources of quality degradation in the real-world: frequency filtering, reverberation, background noise, and digital compression. Second, we leveraged an existing, pre-trained speech foundation model, WavLM, to computationally derive a self-supervised training target that quantified speech degradation using the cosine distance between the clean and degraded versions of each utterance in the embedding space. Next, we trained a transformer-based model to predict these cosine distances, given only the degraded versions of the utterances. Finally, the trained model was evaluated on unseen test corpora of synthetic mixtures, NISQA, and VOiCES. We show that the S3QA model trained on this task accurately predicts degradation cosine distances across a wide range challenging acoustic conditions and is aligned with both behavioral ratings (MOS), speech technology performance (automatic speech recognition) and other important features of the held-out data (e.g., microphone distances). This model provides an automated, scalable method for assessing speech quality across a wide range of acoustic challenges.

eess.AS↗

arXiv2025

pared: Model selection using multi-objective optimization

Motivation: Model selection is a ubiquitous challenge in statistics. For penalized models, model selection typically entails tuning hyperparameters to maximize a measure of fit or minimize out-of-sample prediction error. However, these criteria fail to reflect other desirable characteristics, such as model sparsity, interpretability, or smoothness. Results: We present the R package pared to enable the use of multi-objective optimization for model selection. Our approach entails the use of Gaussian process-based optimization to efficiently identify solutions that represent desirable trade-offs. Our implementation includes popular models with multiple objectives including the elastic net, fused lasso, fused graphical lasso, and group graphical lasso. Our R package generates interactive graphics that allow the user to identify hyperparameter values that result in fitted models which lie on the Pareto frontier. Availability: We provide the R package pared and vignettes illustrating its application to both simulated and real data at https://github.com/priyamdas2/pared.

stat.ME↗

arXiv2007

Five Intermediate-Period Planets from the N2K Sample

We report the detection of five Jovian mass planets orbiting high metallicity stars. Four of these stars were first observed as part of the N2K program and exhibited low RMS velocity scatter after three consecutive observations. However, follow-up observations over the last three years now reveal the presence of longer period planets with orbital periods ranging from 21 days to a few years. HD 11506 is a G0V star with a planet of \msini = 4.74 \mjup in a 3.85 year orbit. HD 17156 is a G0V star with a 3.12 \mjup planet in a 21.2 day orbit. The eccentricity of this orbit is 0.67, one of the highest known for a planet with a relatively short period. The orbital period for this planet places it in a region of parameter space where relatively few planets have been detected. HD 125612 is a G3V star with a planet of \msini = 3.5 \mjup in a 1.4 year orbit. HD 170469 is a G5IV star with a planet of \msini = 0.67 \mjup in a 3.13 year orbit. HD 231701 is an F8V star with planet of 1.08 \mjup in a 142 day orbit. All of these stars have supersolar metallicity. Three of the five stars were observed photometrically but showed no evidence of brightness variability. A transit search conducted for HD 17156 was negative but covered only 25% of the search space and so is not conclusive.

astro-ph↗