Logo image
Enabling Internationalization of Affective Speech Technology Using LLMs
會議論文

Enabling Internationalization of Affective Speech Technology Using LLMs

Bo-Hao Su, Shinji Watanabe 和 Chi-Chun Lee
Proceedings ... Asia-Pacific Signal and Information Processing Association Annual Summit and Conference APSIPA ASC ... (Online), 頁碼.2592-2597
IEEE
2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) (Singapore, Singapore, 22/10/2025–24/10/2025)
22/10/2025

摘要

Benchmark testing Cultural differences Data models Sensors Social robots Speech processing Speech recognition Surveys Training data Systematics
Affective speech technology aspires to equip machines with the ability to sense, interpret, and generate emotionally expressive speech, enabling empathetic assistants, social robots, and digital health companions. Large Audio/Speech Language Models (LALMs/SpeechLMs) now dominate this space: a single model can perform speech recognition, affect detection, and emotion-controlled synthesis, achieving impressive zero-shot generalization. However, we argue that LALMs are not yet internationalized: culturally grounded affect is misread when training data are skewed, leading to mis-recognition of affect, culturally inappropriate responses, and uneven user experiences. This paper surveys the current state of affective speech processing with LALMs, cataloging leading models, their sensing-to-synthesis capabilities, and the databases and metrics used for evaluation. We identify the key obstacle to responsible deployment: the heterogeneity of human vocal expression across cultures, which manifests as data scarcity, model bias, and evaluation blind spots. To address this gap, we propose a research agenda comprising: (i) systematic analysis of cultural variation in vocal affect, (ii) computational strategies for contextualizing LALMs toward culturally sensitive emotion processing, and (iii) benchmarks featuring balanced corpora and culture-aware metrics. By charting these directions, we aim to advance affective speech technology that is globally robust, socially responsible, and truly inclusive. The overall concept is depicted in Figure 1.

相關連結

詳細資料

Logo image