Audio/Video Supervised Independent Vector Analysis through multimodal pilot dependent components

Simple item page
dc.contributor.authorNesta Francescocs
dc.contributor.authorMosayyebpour Saeedcs
dc.contributor.authorKoldovský Zbyněkcs
dc.contributor.authorPaleček Karelcs
dc.date.accessioned2018-09-25T12:13:17Z
dc.date.available2018-09-25T12:13:17Z
dc.date.issued2017cs
dc.description.abstractIndependent Vector Analysis is a powerful tool for estimating the broadband acoustic transfer function between multiple sources and the microphones in the frequency domain. In this work, we consider an extended IVA model which adopts the concept of pilot dependent signals. Without imposing any constraint on the de-mixing system, pilot signals depending on the target source are injected into the model enforcing the permutation of outputs to be consistent over time. A neural network trained on acoustic data and a lip motion detection are jointly used to produce a multimodal pilot signal dependent on the target source. It is shown through experimental results that this structure allows the enhancement of a predefined target source in very difficult and ambiguous scenarios.en
dc.format.extent5cs
dc.identifier.doi10.23919/EUSIPCO.2017.8081388
dc.identifier.isbn978-0-9928626-7-1cs
dc.identifier.urihttps://dspace.tul.cz/handle/15240/31080
dc.identifier.urihttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8081388
dc.language.isoengcs
dc.publisher.cityKos, Greececs
dc.relation.ispartofseries1cs
dc.relation.urihttps://asap.ite.tul.cz/wp-content/uploads/sites/3/2017/06/Eusipco2017b.pdfcs
dc.subjectindependent vector analysiscs
dc.subjectsource separationcs
dc.subjectindependent component analysiscs
dc.subjectspeech enhancementcs
dc.subjectmulti- modal processingcs
dc.titleAudio/Video Supervised Independent Vector Analysis through multimodal pilot dependent componentscs
local.citation.epage1190-1194cs
local.citation.spage1190-1194cs
local.identifier.publikace4536
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Audio_Video Supervised.pdf
Size:
264.34 KB
Format:
Adobe Portable Document Format
Description:
článek
Download
Collections