{"@context":{"@vocab":"https://cir.nii.ac.jp/schema/1.0/","rdfs":"http://www.w3.org/2000/01/rdf-schema#","dc":"http://purl.org/dc/elements/1.1/","dcterms":"http://purl.org/dc/terms/","foaf":"http://xmlns.com/foaf/0.1/","prism":"http://prismstandard.org/namespaces/basic/2.0/","cinii":"http://ci.nii.ac.jp/ns/1.0/","datacite":"https://schema.datacite.org/meta/kernel-4/","ndl":"http://ndl.go.jp/dcndl/terms/","jpcoar":"https://github.com/JPCOAR/schema/blob/master/2.0/"},"@id":"https://cir.nii.ac.jp/crid/1360849945258689792.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.1109/mmsp.2019.8901799"}},{"identifier":{"@type":"URI","@value":"http://xplorestaging.ieee.org/ielx7/8891847/8901684/08901799.pdf?arnumber=8901799"}}],"resourceType":"学術雑誌論文(journal article)","dc:title":[{"@value":"Blink-former: Light-aided beamforming for multiple targets enhancement"}],"description":[{"notation":[{"@value":"We propose a multimodal framework to enhance multiple target sound sources using a conventional microphone array, a video camera, and sound power sensors, called Blinkies, that we have recently developed. Each Blinky consists of a microphone, LEDs, a microcontroller, and a battery. One of the LEDs intensity is varied according to sound power, that is, the Blinky works as a sound-to-light conversion sensor. They are easy to distribute over a large area, and thus, the sound power information therein can be harvested by capturing the LED signals with a video camera. Although these signals are a mixture of contributions from multiple sources, we demonstrate that they can be separated into individual source activities by non-negative matrix factorization. The obtained activities are further utilized to design maximum signal-to-interference-and-noise ratio beamformers enhancing the source signals. We conduct numerical simulations and real experiments to evaluate the performance of this method in diffuse noise environment. The experimental results show that the proposed scheme using Blinkies is superior to competing algorithms, especially at low signal-to-noise ratio."}]}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1380849945258689794","@type":"Researcher","foaf:name":[{"@value":"Robin Scheibler"}],"jpcoar:affiliationName":[{"@value":"Graduate School of System Design, Tokyo Metropolitan University,Tokyo,Japan,191-0065"}]},{"@id":"https://cir.nii.ac.jp/crid/1380849945258689795","@type":"Researcher","foaf:name":[{"@value":"Yukoh Wakabayashi"}],"jpcoar:affiliationName":[{"@value":"Graduate School of System Design, Tokyo Metropolitan University,Tokyo,Japan,191-0065"}]},{"@id":"https://cir.nii.ac.jp/crid/1380849945258689793","@type":"Researcher","foaf:name":[{"@value":"Nobutaka Ono"}],"jpcoar:affiliationName":[{"@value":"Graduate School of System Design, Tokyo Metropolitan University,Tokyo,Japan,191-0065"}]},{"@id":"https://cir.nii.ac.jp/crid/1380849945258689792","@type":"Researcher","foaf:name":[{"@value":"Daiki Horiike"}],"jpcoar:affiliationName":[{"@value":"Graduate School of System Design, Tokyo Metropolitan University,Tokyo,Japan,191-0065"}]}],"publication":{"prism:publicationName":[{"@value":"2019 IEEE 21st International Workshop on Multimedia Signal Processing (MMSP)"}],"dc:publisher":[{"@value":"IEEE"}],"prism:publicationDate":"2019-09","prism:startingPage":"1","prism:endingPage":"6"},"reviewed":"false","dc:rights":["https://doi.org/10.15223/policy-029","https://doi.org/10.15223/policy-037"],"url":[{"@id":"http://xplorestaging.ieee.org/ielx7/8891847/8901684/08901799.pdf?arnumber=8901799"}],"createdAt":"2019-11-25","modifiedAt":"2025-09-04","project":[{"@id":"https://cir.nii.ac.jp/crid/1040000781953131520","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"17F17049"},{"@type":"JGN","@value":"JP17F17049"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-17F17049/"}],"notation":[{"@language":"ja","@value":"音光変換とビデオカメラに基づく多チャンネル音響信号処理の研究"},{"@language":"en","@value":"Multi-channel Audio Signal Processing Based on Sound-to-Light Conversion and Video Camera"}]}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360011144003316864","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Performance measurement in blind audio source separation"}]},{"@id":"https://cir.nii.ac.jp/crid/1360013168828468224","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"End-to-End Training for Acoustic Scene Analysis with Distributed Sound-to-Light Conversion Devices"}]},{"@id":"https://cir.nii.ac.jp/crid/1360588380150532608","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"End-to-end training of acoustic scene classification using distributed sound-to-light conversion devices: verification through simulation experiments"}]},{"@id":"https://cir.nii.ac.jp/crid/1360848663875017728","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Blinkies: Sound-to-light conversion sensors and their application to speech enhancement and sound source localization"}]},{"@id":"https://cir.nii.ac.jp/crid/1360848663876722560","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Multiple far noise suppression in a real environment using transfer-function-gain NMF"}]},{"@id":"https://cir.nii.ac.jp/crid/1360849945129672448","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Multi-modal Blind Source Separation with Microphones and Blinkies"}]},{"@id":"https://cir.nii.ac.jp/crid/1360857692618814336","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Audio Source Separation"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137045037497088","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Nonnegative Matrix Factorization with the Itakura-Saito Divergence: With Application to Music Analysis"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137045858561664","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Pyroomacoustics: A Python Package for Audio Room Simulation and Array Processing Algorithms"}]},{"@id":"https://cir.nii.ac.jp/crid/1361412894994479104","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Blinkies: Open Source Sound-to-Light Conversion Sensors for Large-Scale Acoustic Sensing and Applications"}]},{"@id":"https://cir.nii.ac.jp/crid/1361981471118929152","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"An approach to blind source separation based on temporal structure of speech signals"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107369194327296","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A High-Speed Camera-Based Approach to Massive Sound Sensing With Optical Wireless Acoustic Sensors"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233270413922304","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Stable and fast update rules for independent vector analysis based on auxiliary function technique"}]},{"@id":"https://cir.nii.ac.jp/crid/1364233270976022272","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Two decades of array signal processing research: the parametric approach"}]},{"@id":"https://cir.nii.ac.jp/crid/1370016861961986561","@type":"Product","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"mir_eval: A transparent implementation of common MIR metrics"}]},{"@id":"https://cir.nii.ac.jp/crid/1370016861961986566","@type":"Product","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Convergence-guaranteed multiplicative algorithms for nonnegative matrix factorization with, ß-divergence"}]},{"@id":"https://cir.nii.ac.jp/crid/1370016861961986568","@type":"Product","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Algorithms for non-negative matrix factorization"}]},{"@id":"https://cir.nii.ac.jp/crid/1390282680066051328","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@language":"en","@value":"JNAS: Japanese speech corpus for large vocabulary continuous speech recognition research."}]},{"@id":"https://cir.nii.ac.jp/crid/1390571395581474304","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@language":"en","@value":"Real-Time Pitch Visualization with “Blinky\" Sound-to-Light Conversion Device"}]}],"dataSourceIdentifier":[{"@type":"CROSSREF","@value":"10.1109/mmsp.2019.8901799"},{"@type":"KAKEN","@value":"PRODUCT-22992159"},{"@type":"OPENAIRE","@value":"doi_dedup___::e6303e08c6a69bf8bd34d8bcb841e21c"},{"@type":"CROSSREF","@value":"10.23919/eusipco54536.2021.9616341_references_DOI_DoG4NamzsKaExrMVsfyCSWVBY9K"},{"@type":"CROSSREF","@value":"10.2299/jsp.25.213_references_DOI_DoG4NamzsKaExrMVsfyCSWVBY9K"},{"@type":"CROSSREF","@value":"10.1109/access.2020.2985281_references_DOI_DoG4NamzsKaExrMVsfyCSWVBY9K"},{"@type":"CROSSREF","@value":"10.1186/s13636-024-00369-z_references_DOI_DoG4NamzsKaExrMVsfyCSWVBY9K"}]}