{"ID":2883128,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08715","arxiv_id":"2508.08715","title":"MultiGen: Child-Friendly Multilingual Speech Generator with LLMs","abstract":"Generative speech models have demonstrated significant potential in improving human-machine interactions, offering valuable real-world applications such as language learning for children. However, achieving high-quality, child-friendly speech generation remains challenging, particularly for low-resource languages across diverse languages and cultural contexts. In this paper, we propose MultiGen, a multilingual speech generation model with child-friendly interaction, leveraging LLM architecture for speech generation tailored for low-resource languages. We propose to integrate age-appropriate multilingual speech generation using LLM architectures, which can be used to facilitate young children's communication with AI systems through culturally relevant context in three low-resource languages: Singaporean accent Mandarin, Malay, and Tamil. Experimental results from both objective metrics and subjective evaluations demonstrate the superior performance of the proposed MultiGen compared to baseline methods.","short_abstract":"Generative speech models have demonstrated significant potential in improving human-machine interactions, offering valuable real-world applications such as language learning for children. However, achieving high-quality, child-friendly speech generation remains challenging, particularly for low-resource languages acros...","url_abs":"https://arxiv.org/abs/2508.08715","url_pdf":"https://arxiv.org/pdf/2508.08715v3","authors":"[\"Xiaoxue Gao\",\"Huayun Zhang\",\"Nancy F. Chen\"]","published":"2025-08-12T07:58:48Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.AI\",\"cs.CL\",\"eess.SP\"]","methods":"[\"Large Language Model\"]","has_code":false}