11 papers
Social welfare optimisation under institutional reward and punishment
Van An Nguyen, Vuong Khang Huynh, Huu Loi Bui +8
Institutional incentives are widely used to promote cooperation among autonomous, self-regarding agents, from human societies to multi-agent and AI systems. Existing work typically…
WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models
Hanna Lee, Tan Dat Nguyen, Jaehoon Kang +1
Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to f…
MamTra: A Hybrid Mamba-Transformer Backbone for Speech Synthesis
Tan Dat Nguyen, Sangmin Bae, Joon Son Chung +1
Despite the remarkable quality of LLM-based text-to-speech systems, their reliance on autoregressive Transformers leads to quadratic computational complexity, which severely limits…
Social welfare optimisation in well-mixed and structured populations
Van An Nguyen, Vuong Khang Huynh, Ho Nam Duong +10
Research on promoting cooperation among autonomous, self-regarding agents has often focused on the bi-objective optimisation problem: minimising the total incentive cost while maxi…
SPADE: Structured Pruning and Adaptive Distillation for Efficient LLM-TTS
Tan Dat Nguyen, Jaehun Kim, Ji-Hoon Kim +3
The goal of this paper is to introduce SPADE, a framework for Structured Pruning and Adaptive Distillation for Efficient Large Language Model-based text-to-speech (LLM-TTS). Recent…
MAGE: A Coarse-to-Fine Speech Enhancer with Masked Generative Model
The Hieu Pham, Tan Dat Nguyen, Phuong Thanh Tran +2
Speech enhancement remains challenging due to the trade-off between efficiency and perceptual quality. In this paper, we introduce MAGE, a Masked Audio Generative Enhancer that adv…
AdaptVC: High Quality Voice Conversion with Adaptive Learning
Jaehun Kim, Ji-Hoon Kim, Yeunju Choi +3
The goal of voice conversion is to transform the speech of a source speaker to sound like that of a reference speaker while preserving the original content. A key challenge is to e…
VoiceDiT: Dual-Condition Diffusion Transformer for Environment-Aware Speech Synthesis
Jaemin Jung, Junseok Ahn, Chaeyoung Jung +3
We present VoiceDiT, a multi-modal generative model for producing environment-aware speech and audio from text and visual prompts. While aligning speech with text is crucial for in…
Accelerating Codec-based Speech Synthesis with Multi-Token Prediction and Speculative Decoding
Tan Dat Nguyen, Ji-Hoon Kim, Jeongsoo Choi +4
The goal of this paper is to accelerate codec-based speech synthesis systems with minimum sacrifice to speech quality. We propose an enhanced inference method that allows for flexi…
Wanna hear your voice? A sample is all we need!
The Hieu Pham, Phuong Thanh Tran Nguyen, Xuan Tho Nguyen +2
Research on audio clue-based target speaker extraction (TSE) has focused on modeling mixtures and reference speech, achieving strong results in English due to abundant datasets. Ho…
FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder
Tan Dat Nguyen, Ji-Hoon Kim, Youngjoon Jang +2
The goal of this paper is to generate realistic audio with a lightweight and fast diffusion-based vocoder, named FreGrad. Our framework consists of the following three key componen…