Self-Supervised Generation of Spatial Audio for 360 Video

By Pedro Morgado, Nuno Vasconcelos, Timothy R. Langlois, Oliver Wang. 2018

200 citations recorded by the source corpus.

We introduce an approach to convert mono audio recorded by a 360° video camera into spatial audio, a representation of the distribution of sound over the full viewing sphere. Spatial audio is an important component of immersive 360° video viewing, but spatial audio microphones are still rare in current 360° video production. Our system consists of end-to-end trainable neural networks that separate individual sound sources and localize them on the viewing sphere, conditioned on multi-modal analysis from the audio and 360° video frames. We introduce several datasets, including one filmed ourselves, and one collected in-the-wild from YouTube, consisting of 360° videos uploaded with spatial audio. During training, ground truth spatial audio serves as self-supervision and a mixed down mono track forms the input to our network. Using our approach we show that it is possible to infer the spatial localization of sounds based only on a synchronized 360° video and the mono audio track.

Subfields: Computer Vision and Pattern Recognition, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Speech & Audio

In Signal Processing

Citations in the corpus

Ego4D: Around the World in 3,000 Hours of Egocentric Video (2021, background): “Meanwhile, visual information is increasingly used in historically audio-only tasks like speech transcription, voice recognition, audio spatialization [5, 80, 104, 161], speaker diarization [10,83], and source separation [57,78,82].”
AVLnet: Learning Audio-Visual Language Representations from Instructional Videos (2020, background): “ded audio source separation [43–48], sound generation from silent videos [39, 49], sound localization in video frames [50, 51], face and voice association [52, 53], and video-based audio localization [54, 55]. While our work has a similar focus on audio and video, instead of learning the source of a”
Audio-Visual Instance Discrimination with Cross-Modal Agreement (2020, background): “In particular, audio self-supervision has shown to be useful for localization [3, 71], lip-speech synchronization [12] and visual representation learning [2, 36, 58] and audio spatialization [52].”
Self-Supervised Moving Vehicle Tracking With Stereo Sound (2019, background): “[18, 26] also explored how to generate spatial sound for videos.”
VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency (2021, background): “Apart from source separation, recent inspiring work integrates both audio and visual cues on an array of other tasks including self-supervised representation learning [57, 6, 8, 55, 41, 23], localizing sounds in video frames [7, 66, 71, 36], generating sounds from video [56, 84, 25, 47, 83], and act”
Deep Audio-visual Learning: A Survey (2020, background): “In contrast to previous approaches that require training a separate model for each speaker of interest (speaker-dependent models), Ephrat et al. [7] proposed a speaker-independent model that was only trained once and was then applicable to any speaker.”
Grounding Spoken Words in Unlabeled Video (2019, background): “This idea has been further developed for visually-guided audio source separation [8,18,19], generating sounds from silent videos [17,21], localizing sounds in video frames [3, 19], learning association of faces and voices [13,15], and video-based audio spatialization [7,14].”
Audio-Visual Embodied Navigation (2019, background): “This includes interesting directions for synthesizing sounds for video [73, 18, 116], spatializing monaural sounds [33, 67], sound source separation [32, 72, 115, 29, 34], cross-modal feature learning [112, 113, 74], audio-visual target tracking [35, 9, 10, 3], and learning material properties [73].”
Co-Separating Sounds of Visual Objects (2019, methodology): “A related design for multi-modal feature fusion is also used in [13, 30, 31] for audio spatialization and separation.”
2.5D Visual Sound (2018, methodology): “YT-CLEAN This dataset contains in-the-wild 360◦ videos from YouTube crawled by [28] using queries related to spatial audio.”
SoundSpaces: Audio-Visual Navigation in 3D Environments (2019, background): “This includes interesting directions for synthesizing sounds for video [71,16,110], spatializing sound [65,32], sound source separation [109,31,70,26,33], cross-modal feature learning [106,107,72,30], AV tracking [34,8,9,2], and learning material properties [71].”