SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909677601685504 |
|---|---|
| author | Dagli, Rishit Prakash, Shivesh Wu, Robert Khosravani, Houman |
| author_facet | Dagli, Rishit Prakash, Shivesh Wu, Robert Khosravani, Houman |
| contents | Generating combined visual and auditory sensory experiences is critical for the consumption of immersive content. Recent advances in neural generative models have enabled the creation of high-resolution content across multiple modalities such as images, text, speech, and videos. Despite these successes, there remains a significant gap in the generation of high-quality spatial audio that complements generated visual content. Furthermore, current audio generation models excel in either generating natural audio or speech or music but fall short in integrating spatial audio cues necessary for immersive experiences. In this work, we introduce SEE-2-SOUND, a zero-shot approach that decomposes the task into (1) identifying visual regions of interest; (2) locating these elements in 3D space; (3) generating mono-audio for each; and (4) integrating them into spatial audio. Using our framework, we demonstrate compelling results for generating spatial audio for high-quality videos, images, and dynamic images from the internet, as well as media generated by learned approaches. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06612 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound Dagli, Rishit Prakash, Shivesh Wu, Robert Khosravani, Houman Computer Vision and Pattern Recognition Machine Learning Sound Audio and Speech Processing Generating combined visual and auditory sensory experiences is critical for the consumption of immersive content. Recent advances in neural generative models have enabled the creation of high-resolution content across multiple modalities such as images, text, speech, and videos. Despite these successes, there remains a significant gap in the generation of high-quality spatial audio that complements generated visual content. Furthermore, current audio generation models excel in either generating natural audio or speech or music but fall short in integrating spatial audio cues necessary for immersive experiences. In this work, we introduce SEE-2-SOUND, a zero-shot approach that decomposes the task into (1) identifying visual regions of interest; (2) locating these elements in 3D space; (3) generating mono-audio for each; and (4) integrating them into spatial audio. Using our framework, we demonstrate compelling results for generating spatial audio for high-quality videos, images, and dynamic images from the internet, as well as media generated by learned approaches. |
| title | SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound |
| topic | Computer Vision and Pattern Recognition Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.06612 |