Taskmaster is a British television show that combines comedic performance with a formal scoring system. Despite the appearance of structured competition, it remains unclear whether scoring dynamics contribute meaningfully to audience engagement. We conducted a statistical analysis of 162 episodes across 18 series, using fifteen episode-level metrics to quantify rank volatility, point spread, lead changes, and winner dominance. None of these metrics showed a significant association with IMDb ratings, even after controlling for series effects. Long-term trends suggest that average points have increased over time, while volatility has slightly declined and rank spread has remained stable. These patterns indicate an attempt to enhance competitive visibility without altering the show's structural equilibrium. We also analyzed contestant rank trajectories and identified five recurring archetypes describing performance styles. These patterns suggest that viewer interest is shaped more by contestant behavior than by game mechanics.

Text-to-speech (TTS) has shown great progress in recent years. However, most existing TTS systems offer only coarse and rigid emotion control, typically via discrete emotion labels or a carefully crafted and detailed emotional text prompt, making fine-grained emotion manipulation either inaccessible or unstable. These models also require extensive, high-quality datasets for training. To address these limitations, we propose EmoSteer-TTS, a novel training-free approach, to achieve fine-grained speech emotion control (conversion, interpolation, erasure) by activation steering. We first empirically observe that modifying a subset of the internal activations within a flow matching-based TTS model can effectively alter the emotional tone of synthesized speech. Building on this insight, we then develop a training-free and efficient algorithm, including activation extraction, emotional token searching, and inference-time steering, which can be seamlessly integrated into a wide range of pretrained models (e.g., F5-TTS, CosyVoice2, and E2-TTS). In addition, to derive effective steering vectors, we construct a curated emotional speech dataset with diverse speakers. Extensive experiments demonstrate that EmoSteer-TTS enables fine-grained, interpretable, and continuous control over speech emotion, outperforming the state-of-the-art (SOTA). To the best of our knowledge, this is the first method that achieves training-free and continuous fine-grained emotion control in TTS. Demo samples are available at https://emosteer-tts-demo.pages.dev/.

Large Language Models like GPT-4 adjust their responses not only based on the question asked, but also on how it is emotionally phrased. We systematically vary the emotional tone of 156 prompts - spanning controversial and everyday topics - and analyze how it affects model responses. Our findings show that GPT-4 is three times less likely to respond negatively to a negatively framed question than to a neutral one. This suggests a "rebound" bias where the model overcorrects, often shifting toward neutrality or positivity. On sensitive topics (e.g., justice or politics), this effect is even more pronounced: tone-based variation is suppressed, suggesting an alignment override. We introduce concepts like the "tone floor" - a lower bound in response negativity - and use tone-valence transition matrices to quantify behavior. Visualizations based on 1536-dimensional embeddings confirm semantic drift based on tone. Our work highlights an underexplored class of biases driven by emotional framing in prompts, with implications for AI alignment and trust. Code and data are available at: https://github.com/bardolfranck/llm-responses-viewer

Television networks face high financial risk when making programming decisions, often relying on limited historical data to forecast episodic viewership. This study introduces a machine learning framework that integrates natural language processing (NLP) features from over 25000 television episodes with traditional viewership data to enhance predictive accuracy. By extracting emotional tone, cognitive complexity, and narrative structure from episode dialogue, we evaluate forecasting performance using SARIMAX, rolling XGBoost, and feature selection models. While prior viewership remains a strong baseline predictor, NLP features contribute meaningful improvements for some series. We also introduce a similarity scoring method based on Euclidean distance between aggregate dialogue vectors to compare shows by content. Tested across diverse genres, including Better Call Saul and Abbott Elementary, our framework reveals genre-specific performance and offers interpretable metrics for writers, executives, and marketers seeking data-driven insight into audience behavior.

Vision-language models (VLMs) have advanced rapidly in processing multimodal information, but their ability to reconcile conflicting signals across modalities remains underexplored. This work investigates how VLMs process ASCII art, a unique medium where textual elements collectively form visual patterns, potentially creating semantic-visual conflicts. We introduce a novel evaluation framework that systematically challenges five state-of-the-art models (including GPT-4o, Claude, and Gemini) using adversarial ASCII art, where character-level semantics deliberately contradict global visual patterns. Our experiments reveal a strong text-priority bias: VLMs consistently prioritize textual information over visual patterns, with visual recognition ability declining dramatically as semantic complexity increases. Various mitigation attempts through visual parameter tuning and prompt engineering yielded only modest improvements, suggesting that this limitation requires architectural-level solutions. These findings uncover fundamental flaws in how current VLMs integrate multimodal information, providing important guidance for future model development while highlighting significant implications for content moderation systems vulnerable to adversarial examples.

This paper examines the role of manner-of-motion verbs in shaping subjective temporal perception and emotional resonance. Through four complementary studies, we explore how these verbs influence the conceptualization of time, examining their use in literal and metaphorical (temporal) contexts. Our findings reveal that faster verbs (e.g., fly, zoom) evoke dynamic and engaging temporal experiences, often linked to positive emotions and greater agency. In contrast, slower verbs (e.g., crawl, drag) convey passivity, monotony, and negative emotions, reflecting tedious or constrained experiences of time. These effects are amplified in metaphorical contexts, where manner verbs encode emotional and experiential nuances that transcend their literal meanings. We also find that participants prefer manner verbs over path verbs (e.g., go, pass) in emotionally charged temporal contexts, as manner verbs capture the experiential and emotional qualities of time more effectively. These findings highlight the interplay between language, motion, and emotion in shaping temporal perception, offering insights into how linguistic framing influences subjective experiences of time.

Queries to large language models (LLMs) can be divided into two parts: the instruction/question and the accompanying context. The context for retrieval-augmented generation (RAG) systems in most benchmarks comes from Wikipedia or Wikipedia-like texts which are written in a neutral and factual tone. However, when RAG systems retrieve internet-based content, they encounter text with diverse tones and linguistic styles, introducing challenges for downstream tasks. The Reading with Intent task addresses this issue by evaluating how varying tones in context passages affect model performance. Building on prior work that focused on sarcasm, we extend this paradigm by constructing a dataset where context passages are transformed to $11$ distinct emotions using a better synthetic data generation approach. Using this dataset, we train an emotion translation model to systematically adapt passages to specified emotional tones. The human evaluation shows that the LLM fine-tuned to become the emotion-translator benefited from the synthetically generated data. Finally, the emotion-translator is used in the Reading with Intent task to transform the passages to a neutral tone. By neutralizing the passages, it mitigates the challenges posed by sarcastic passages and improves overall results on this task by about $3\%$.

Recent progress in audio-language modeling, such as automated audio captioning, has benefited from training on synthetic data generated with the aid of large-language models. However, such approaches for environmental sound captioning have primarily focused on audio event tags and have not explored leveraging emotional information that may be present in recordings. In this work, we explore the benefit of generating emotion-augmented synthetic audio caption data by instructing ChatGPT with additional acoustic information in the form of estimated soundscape emotion. To do so, we introduce EmotionCaps, an audio captioning dataset comprised of approximately 120,000 audio clips with paired synthetic descriptions enriched with soundscape emotion recognition (SER) information. We hypothesize that this additional information will result in higher-quality captions that match the emotional tone of the audio recording, which will, in turn, improve the performance of captioning models trained with this data. We test this hypothesis through both objective and subjective evaluation, comparing models trained with the EmotionCaps dataset to multiple baseline models. Our findings challenge current approaches to captioning and suggest new directions for developing and assessing captioning models.

On Thursday, Microsoft researchers announced a new text-to-speech AI model called VALL-E that can closely simulate a person's voice when given a three-second audio sample. Once it learns a specific voice, VALL-E can synthesize audio of that person saying anything--and do it in a way that attempts to preserve the speaker's emotional tone. Its creators speculate that VALL-E could be used for high-quality text-to-speech applications, speech editing where a recording of a person could be edited and changed from a text transcript (making them say something they originally didn't), and audio content creation when combined with other generative AI models like GPT-3. Microsoft calls VALL-E a "neural codec language model," and it builds off of a technology called EnCodec, which Meta announced in October 2022. Unlike other text-to-speech methods that typically synthesize speech by manipulating waveforms, VALL-E generates discrete audio codec codes from text and acoustic prompts.

Microsoft has shown off its latest research in text-to-speech AI with a model called VALL-E that can simulate someone's voice from just a three-second audio sample, Ars Technica has reported. The speech can not only match the timbre but also the emotional tone of the speaker, and even the acoustics of a room. It could one day be used for customized or high-end text-to-speech applications, though like deepfakes, it carries risks of misuse. VALL-E is what Microsoft calls a "neural codec language model." It's derived from Meta's AI-powered compression neural net Encodec, generating audio from text input and short samples from the target speaker.