# MultiGen: Child-Friendly Multilingual Speech Generator with LLMs

arXiv: https://arxiv.org/abs/2508.08715 · HTML: https://mlsanity.com/paper/2508.08715/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 44 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Builds on (most cited first, 20 of 20)

- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech](https://mlsanity.com/paper/2106.06103/) (2021)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis](https://mlsanity.com/paper/1803.09017/) (2018)
- [VoiceBench: Benchmarking LLM-Based Voice Assistants](https://mlsanity.com/paper/2410.17196/) (2024)
- [FastPitch: Parallel Text-to-speech with Pitch Prediction](https://mlsanity.com/paper/2006.06873/) (2020)
- [MathDial: A Dialogue Tutoring Dataset with Rich Pedagogical Properties Grounded in Math Reasoning Problems](https://mlsanity.com/paper/2305.14536/) (2023)
- [VALL-E 2: Neural Codec Language Models are Human Parity Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2406.05370/) (2024)
- [SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages](https://mlsanity.com/paper/2406.10118/) (2024)
- [Fine-grained Emotion Strength Transfer, Control and Prediction for Emotional Speech Synthesis](https://mlsanity.com/paper/2011.08477/) (2020)
- [Emotional speech synthesis with rich and granularized control](https://mlsanity.com/paper/1911.01635/) (2019)
- [A Vector Quantized Approach for Text to Speech Synthesis on Real-World Spontaneous Speech](https://mlsanity.com/paper/2302.04215/) (2023)
- [Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling](https://mlsanity.com/paper/2312.11947/) (2023)
- [TTSlow: Slow Down Text-to-Speech with Efficiency Robustness Evaluations](https://mlsanity.com/paper/2407.01927/) (2024)
- [Multilingual Speech Evaluation: Case Studies on English, Malay and Tamil](https://mlsanity.com/paper/2107.03675/) (2021)
- [An Initial Investigation of Language Adaptation for TTS Systems under Low-resource Scenarios](https://mlsanity.com/paper/2406.08911/) (2024)
- [MERaLiON-SpeechEncoder: Towards a Speech Foundation Model for Singapore and Beyond](https://mlsanity.com/paper/2412.11538/) (2024)
- [Prompt-Unseen-Emotion: Zero-shot Expressive Speech Synthesis with Prompt-LLM Contextual Knowledge for Mixed Emotions](https://mlsanity.com/paper/2506.02742/) (2025)
- [Text-to-speech synthesis based on latent variable conversion using diffusion probabilistic model and variational autoencoder](https://mlsanity.com/paper/2212.08329/) (2022)
- [SingaKids: A Multilingual Multimodal Dialogic Tutor for Language Learning](https://mlsanity.com/paper/2506.02412/) (2025)

## Built on by (most cited first, 1 of 1)

- [The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models](https://mlsanity.com/paper/2605.25510/) (2026)

## Abstract (arXiv)

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.