As the scale of generative models continues to grow, efficient reuse and adaptation of pre-trained models have become crucial considerations. In this work, we propose Voicebox Adapter, a novel approach that integrates fine-grained conditions into a pre-trained Voicebox speech generation model using a cross-attention module. To ensure a smooth integration of newly added modules with pre-trained ones, we explore various efficient fine-tuning approaches. Our experiment shows that the LoRA with bias-tuning configuration yields the best performance, enhancing controllability without compromising speech quality. Across three fine-grained conditional generation tasks, we demonstrate the effectiveness and resource efficiency of Voicebox Adapter. Follow-up experiments further highlight the robustness of Voicebox Adapter across diverse data setups.
@article{arxiv.2406.06251,
title = {Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning},
author = {Chung-Ming Chien and Andros Tjandra and Apoorv Vyas and Matt Le and Bowen Shi and Wei-Ning Hsu},
journal= {arXiv preprint arXiv:2406.06251},
year = {2024}
}