1. Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning
- Author
-
Chien, Chung-Ming, Tjandra, Andros, Vyas, Apoorv, Le, Matt, Shi, Bowen, and Hsu, Wei-Ning
- Subjects
Electrical Engineering and Systems Science - Audio and Speech Processing ,Computer Science - Computation and Language - Abstract
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., Comment: Accepted by InterSpeech 2024
- Published
- 2024