How U.S. presidents explain war tells you everything about the moment—and everything about the president.

#History #Leadership #PresidentialHistory #WarPowers #PoliticalHistory #AmericanHistory #Geopolitics #CivicLiteracy #SpeechAnalysis #Politics

Predicting Ultra-High Risk Outcomes Using Linguistic and Acoustic Measures From High-Risk Social Challenge Recordings: mHealth Longitudinal Cohort Exploratory Study Background: Early detection of individuals at ultra-high risk (UHR) for psychosis is critical for timely intervention and improving clinical outcomes. However, current UHR assessments which rely heavily on psychometric tools, often suffer from low specificity. Speech-based Machine Learning (ML) prediction models can potentially be used to improve prognostic accuracy. However, existing studies often utilised used long, open-ended speech tasks which limits scalability. The High-Risk Social Challenge (HiSoC) is a short 45-second speech task designed to measure social functioning in UHR individuals. If the HiSoC task is able to capture predictive signals, it may serve as an effective and scalable speech task for future prediction models. Objective: We explore whether linguistic and acoustic features extracted from the HiSoC task are associated with UHR outcomes and if they are predictive of different UHR outcomes. Methods: Audio recordings of HiSoC task responses were collected from 41 UHR participants enrolled in the Longitudinal Youth at Risk (LYRIK) study. 12 individuals converted to psychosis (CVT), 15 remitted from UHR status (RMT), and 14 maintained UHR status (MNT). Responses from the CVT group were obtained within 12 months of psychosis onset, while responses from the RMT and MNT groups were collected at baseline. Linguistic features analysed included Words per Minute (WPM), Articulation Rate (AR), Dysfluency (DF), and Sequential Coherence (SC). Acoustic features comprised the mean and standard deviation of fundamental frequency, the mean and standard deviation of intensity, and HF500. Feature differential analysis was conducted via multivariate linear regression. Linear Support Vector Machines (SVMs) were trained as outcome prediction models. Nested cross-validation was employed to estimate the generalizability error. Models were principally evaluated on balanced accuracy (BA). Results: The CVT group exhibited lower WPM (adj.P=.024) and higher DF (adj.P=.004) compared to the RMT group. No significant differences were found in AR, SC, or acoustic measures across outcome groups. 2 models outperformed random guess, namely the models using linguistic variables (BA=0.741, 95% CI [0.521, 0.882]) and linguistic + acoustic variables (BA=0.851, 95% CI [0.508, 0.944]). Conclusions: Linguistic features extracted from a short speech task exhibit a measurable difference between outcome groups. Our findings support the #feasibility of using signals extracted from the HiSoC task recordings to predict remission in UHR participants.

JMIR Formative Res: Predicting Ultra-High Risk Outcomes Using Linguistic and Acoustic Measures From High-Risk Social Challenge Recordings: mHealth Longitudinal Cohort Exploratory Study #MentalHealth #Psychosis #MachineLearning #AIinHealthcare #SpeechAnalysis

“Inherited a Mess” — The Most Reliable Political Lie
#TrumpSpeech #PoliticalRhetoric #InheritedAMess #SpeechAnalysis

Performance of Automatic Speech Analysis in Detecting #depression: Systematic Review and Meta-Analysis Background: Despite the high prevalence and significant burden of #depression, underdiagnosis remains a persistent challenge. Automatic speech analysis (ASA) has emerged as a promising method for #depression assessment. However, a comprehensive quantitative synthesis evaluating its diagnostic accuracy is still lacking. Objective: This systematic review and meta-analysis aimed to assess the diagnostic performance of ASA in detecting #depression, considering both machine learning and deep learning #Approaches. Methods: We conducted a systematic search across 8 databases, including MEDLINE, PsycInfo, Embase, CINAHL, IEEE Xplore, ACM #Digital Library, Scopus, and Google Scholar from January 2013 to April 1, 2025. We included studies published in English that evaluated the accuracy of ASA for detecting #depression, and reported performance metrics such as accuracy, sensitivity, specificity, precision, or confusion matrices. Study quality was assessed using a modified version of the Quality Assessment of Studies of Diagnostic Accuracy-Revised. A 3-level meta-analysis was performed to estimate the pooled highest and lowest accuracy, sensitivity, specificity, and precision. Meta-regressions and subgroup analyses were performed to explore heterogeneity across various factors, including type of publication, artificial intelligence algorithms, speech features, speech-eliciting tasks, ground truth assessment, validation #Approach, dataset, dataset language, participants’ mean age, and sample size. Results: Of the 1345 records identified, 105 studies met the inclusion criteria. The pooled mean of the highest accuracy, sensitivity, specificity, and precision were 0.81 (95% CI 0.79 to 0.83), 0.84 (95% CI 0.81 to 0.86), 0.83 (95% CI 0.79 to 0.86), and 0.81 (95% CI 0.77 to 0.84), respectively, whereas the pooled mean of the lowest accuracy, sensitivity, specificity, and precision were 0.66 (95% CI 0.63 to 0.69), 0.63 (95% CI 0.58 to 0.68), 0.60 (95% CI 0.55 to 0.66), and 0.64 (95% CI 0.58 to 0.70), respectively. Conclusions: ASA shows promise as a method for detecting #depression, though its readiness for clinical #Application as a standalone tool remains limited. At present, it should be regarded as a complementary method, with potential #Applications across diverse contexts. Further high-quality, peer-reviewed studies are needed to support the development of robust, generalizable models and to advance this emerging field. Trial Registration: PROSPERO CRD42023444431; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023444431

JMIR Mental Health: Performance of Automatic Speech Analysis in Detecting #depression: Systematic Review and Meta-Analysis #Depression #MentalHealth #SpeechAnalysis #MachineLearning #DeepLearning

Temporal-Aware Iterative Speech Model Improves AI Dementia Detection

TAI‑Speech, a temporal‑aware AI framework that analyzes raw speech, achieved an AUC of 0.839 and 80.6% accuracy on the DementiaBank dataset without using transcripts. Read more: getnews.me/temporal-aware-iterative... #dementia #speechanalysis #ai

MMSE-Calibrated Few-Shot Prompting Advances Alzheimer's Detection

Researchers reported that MMSE‑Proxy Prompting reached 0.82 accuracy and a 0.86 AUC on the ADReSS speech transcript dataset, with results submitted on 24 September 2025. Read more: getnews.me/mmse-calibrated-few-shot... #alzheimers #llm #speechanalysis

"New West Point cadet challenge: construct a coherent sentence using only words from the President's address. So far, all attempts have resulted in a spontaneous combustion of the whiteboards. #CadetStruggles #SpeechAnalysis"

I asked Chat to analyze the speech patterns for Trump vs Obama.

A: “Trump talks like he’s texting a buddy (4th-grade level). Obama sounds like he’s giving a TED Talk (10th-grade). One hits your gut. The other hits your brain.”

#Trump
#Obama
#SpeechAnalysis
#SimpleVsSmart

Tap to chime in. Agree?

🧠💬 Can speech reveal motor states in Parkinson’s disease? Our latest study shows: Yes, it can. 📄 rdcu.be/ekrQg

Proud to share this work with an amazing team and the @speedy-lab.bsky.social

#Parkinsons #SpeechAnalysis #MachineLearning #DigitalBiomarkers

A Signal of Future Alzheimer's May Hide in The Way You Speak Early warnings could make all the difference.

A Signal of Future Alzheimer's May Hide in The Way You Speak #Science #HealthandMedicine #Neurology #AlzheimersResearch #SpeechAnalysis

Discover the truth behind Patrick Henry's iconic 'Give me liberty or give me death' speech. #PatrickHenry #LibertyOrDeath #HistoricalMystery #AmericanHistory #SpeechAnalysis #FireyOratory #WilliamWirt #FoundingFathers #HistoryUncovered #PublicSpeaking

Data shows Spielberg, not Weinstein, was most thanked at Oscars - even more than God during peak years
stephenfollows.com/p/harvey-weinstein-thank...
#oscars #dataanalysis #hollywood #speechanalysis #entertainmentindustry

Exploring Speech Biosignatures for Traumatic Brain Injury and Neurodegeneration: Pilot Machine Learning Study Background: Changes in various speech features have been linked to various neurological and mental health-related pathologies; these changes can often be detected years before a definitive clinical diagnosis. With the growing interest in using speech…

Exploring Speech Biosignatures for Traumatic Brain Injury and Neurodegeneration: Pilot Machine Learning Study #Neuroscience #SpeechAnalysis #TraumaticBrainInjury #Neurodegeneration #MachineLearning