9 citations · 17 across the 11 of their papers we have counts for
5 papers · 1 filter
Monotonicity-Guided Semantic Alignment for Zero-shot Multispeaker Image-to-Speech Synthesis
Lijun Wang, Yixian Lu, Shogo Okada
Direct image-to-speech (Img2Sp) poses an alignment challenge in mapping visual content to ordered speech sequences, as images permit multiple spoken descriptions and lack monotonic…
Cross-lingual Functional Vectors for Emotion Detection in Large Language Models
Jieying Xue, Phuong Minh Nguyen, Minh Le Nguyen +1
Function vectors (FVs) have recently emerged as a promising mechanism for steering the behavior of large language models (LLMs) by injecting task-specific latent direction represen…
Multimodal Rapport Estimation in Real-World HRI
Akihiro Sakuramoto, Takato Hayashi, Ryo Miyoshi +2
Evaluating interaction quality in real-world HRI is an important challenge. If interaction quality can be estimated reliably, the results can be used to improve dialogue strategies…
Speech Signals Complement LLMs for Predicting Interpersonal Attraction in Speed Dating
Yuriko Kikuchi, Takato Hayashi, Ryusei Kimura +3
Large language models (LLMs) can predict interpersonal attraction from conversation transcripts, but it remains unclear what a speech predictor can add beyond transcript-only LLM p…
XPASS-Vis: A Dataset for Cross-Domain Personalized Image Aesthetic Assessment
Takato Hayashi, Hiroaki Takahara, Candy Olivia Mawalim +4
Personalized image aesthetic assessment (PIAA) seeks to model, at the individual level, the subjective nature of aesthetic judgments toward artworks and photographs. Aesthetic pref…