Authors
- Koichi Saito
- Dongjun Kim*
- Takashi Shibuya
- Chieh-Hsin Lai
- Zhi Zhong*
- Yuhta Takida
- Yuki Mitsufuji
* External authors
Venue
- NeurIPS-24
Date
- 2025
SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation
Koichi Saito
Dongjun Kim*
Zhi Zhong*
* External authors
NeurIPS-24
2025
Abstract
Sound content is an indispensable element for multimedia works such as video games, music, and films. Recent high-quality diffusion-based sound generation models can serve as valuable tools for the creators. However, despite producing high-quality sounds, these models often suffer from slow inference speeds. This drawback burdens creators, who typically refine their sounds through trial and error to align them with their artistic intentions. To address this issue, we introduce Sound Consistency Trajectory Models (SoundCTM). Our model enables flexible transitioning between high-quality 1-step sound generation and superior sound quality through multi-step generation. This allows creators to initially control sounds with 1-step samples before refining them through multi-step generation. While CTM fundamentally achieves flexible 1-step and multi-step generation, its impressive performance heavily depends on an additional pretrained feature extractor and an adversarial loss, which are expensive to train and not always available in other domains. Thus, we reframe CTM's training framework and introduce a novel feature distance by utilizing the teacher's network for a distillation loss. Additionally, while distilling classifier-free guided trajectories, we train conditional and unconditional student models simultaneously and interpolate between these models during inference. We also propose training-free controllable frameworks for SoundCTM, leveraging its flexible sampling capability. SoundCTM achieves both promising 1-step and multi-step real-time sound generation without using any extra off-the-shelf networks. Furthermore, we demonstrate SoundCTM's capability of controllable sound generation in a training-free manner.
Related Publications
We present Music Arena, an open platform for scalable human preference evaluation of text-to-music (TTM) models. Soliciting human preferences via listening studies is the gold standard for evaluation in TTM, but these studies are expensive to conduct and difficult to compare…
This paper explores the use of unlearning methods for training data attribution (TDA) in music generative models trained on large-scale datasets. TDA aims to identify which specific training data points contributed to the generation of a particular output from a specific mod…
Blind inverse problems, where both the target data and forward operator are unknown, are crucial to many computer vision applications. Existing methods often depend on restrictive assumptions such as additional training, operator linearity, or narrow image distributions, thu…
JOIN US
Shape the Future of AI with Sony AI
We want to hear from those of you who have a strong desire
to shape the future of AI.