MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911987426918400 |
|---|---|
| author | Kamath, Purnima Gupta, Chitralekha Nanayakkara, Suranga |
| author_facet | Kamath, Purnima Gupta, Chitralekha Nanayakkara, Suranga |
| contents | Sound morphing is the process of gradually and smoothly transforming one sound into another to generate novel and perceptually hybrid sounds that simultaneously resemble both. Recently, diffusion-based text-to-audio models have produced high-quality sounds using text prompts. However, granularly controlling the semantics of the sound, which is necessary for morphing, can be challenging using text. In this paper, we propose \textit{MorphFader}, a controllable method for morphing sounds generated by disparate prompts using text-to-audio models. By intercepting and interpolating the components of the cross-attention layers within the diffusion process, we can create smooth morphs between sounds generated by different text prompts. Using both objective metrics and perceptual listening tests, we demonstrate the ability of our method to granularly control the semantics in the sound and generate smooth morphs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07260 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Models Kamath, Purnima Gupta, Chitralekha Nanayakkara, Suranga Audio and Speech Processing Sound morphing is the process of gradually and smoothly transforming one sound into another to generate novel and perceptually hybrid sounds that simultaneously resemble both. Recently, diffusion-based text-to-audio models have produced high-quality sounds using text prompts. However, granularly controlling the semantics of the sound, which is necessary for morphing, can be challenging using text. In this paper, we propose \textit{MorphFader}, a controllable method for morphing sounds generated by disparate prompts using text-to-audio models. By intercepting and interpolating the components of the cross-attention layers within the diffusion process, we can create smooth morphs between sounds generated by different text prompts. Using both objective metrics and perceptual listening tests, we demonstrate the ability of our method to granularly control the semantics in the sound and generate smooth morphs. |
| title | MorphFader: Enabling Fine-grained Controllable Morphing with Text-to-Audio Models |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.07260 |