Binaural SoundNet: Predicting Semantics, Depth and Motion With Binaural Sounds

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00364658" target="_blank" >RIV/68407700:21230/23:00364658 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1109/TPAMI.2022.3155643" target="_blank" >https://doi.org/10.1109/TPAMI.2022.3155643</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TPAMI.2022.3155643" target="_blank" >10.1109/TPAMI.2022.3155643</a>

Result language

angličtina

Original language name

Binaural SoundNet: Predicting Semantics, Depth and Motion With Binaural Sounds

Original language description

Humans can robustly recognize and localize objects by using visual and/or auditory cues. While machines are able to do the same with visual data already, less work has been done with sounds. This work develops an approach for scene understanding purely based on binaural sounds. The considered tasks include predicting the semantic masks of sound-making objects, the motion of sound-making objects, and the depth map of the scene. To this aim, we propose a novel sensor setup and record a new audio-visual dataset of street scenes with eight professional binaural microphones and a 360$mathrm{<^>{circ }}$& LCIRC;camera. The co-existence of visual and audio cues is leveraged for supervision transfer. In particular, we employ a cross-modal distillation framework that consists of multiple vision 'teacher' methods and a sound 'student' method - the student method is trained to generate the same results as the teacher methods do. This way, the auditory system can be trained without using human annotations. To further boost the performance, we propose another novel auxiliary task, coined Spatial Sound Super-Resolution, to increase the directional resolution of sounds. We then formulate the four tasks into one end-to-end trainable multi-tasking network aiming to boost the overall performance. Experimental results show that 1) our method achieves good results for all four tasks, 2) the four tasks are mutually beneficial - training them together achieves the best performance, 3) the number and orientation of microphones are both important, and 4) features learned from the standard spectrogram and features obtained by the classic signal processing pipeline are complementary for auditory perception tasks. The data and code are released on the project page: https://www.trace.ethz.ch/publications/2020/sound_perception/index.html.

Czech name

—

Czech description

—

Type

J_imp - Article in a specialist periodical, which is included in the Web of Science database

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Research Center for Informatics</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year

2023

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Name of the periodical

IEEE Transactions on Pattern Analysis and Machine Intelligence

ISSN

0162-8828

e-ISSN

1939-3539

Volume of the periodical

45

Issue of the periodical within the volume

1

Country of publishing house

US - UNITED STATES

Number of pages

14

Pages from-to

123-136

UT code for WoS article

000899419900008

EID of the result in the Scopus database

2-s2.0-85125740373