{"@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/1360022497271473536.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.1109/icassp39728.2021.9414264"}},{"identifier":{"@type":"URI","@value":"http://xplorestaging.ieee.org/ielx7/9413349/9413350/09414264.pdf?arnumber=9414264"}},{"identifier":{"@type":"DOI","@value":"10.48550/arxiv.2108.01836"}}],"dc:title":[{"@value":"Blind and Neural Network-Guided Convolutional Beamformer for Joint Denoising, Dereverberation, and Source Separation"}],"description":[{"notation":[{"@value":"This paper proposes an approach for optimizing a Convolutional BeamFormer (CBF) that can jointly perform denoising (DN), dereverberation (DR), and source separation (SS). First, we develop a blind CBF optimization algorithm that requires no prior information on the sources or the room acoustics, by extending a conventional joint DR and SS method. For making the optimization computationally tractable, we incorporate two techniques into the approach: the Source-Wise Factorization (SW-Fact) of a CBF and the Independent Vector Extraction (IVE). To further improve the performance, we develop a method that integrates a neural network(NN) based source power spectra estimation with CBF optimization by an inverse-Gamma prior. Experiments using noisy reverberant mixtures reveal that our proposed method with both blind and NN-guided scenarios greatly outperforms the conventional state-of-the-art NN-supported mask-based CBF in terms of the improvement in automatic speech recognition and signal distortion reduction performance."}]},{"notation":[{"@value":"Accepted by IEEE ICASSP 2021"}]}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1380022497271473539","@type":"Researcher","foaf:name":[{"@value":"Tomohiro Nakatani"}],"jpcoar:affiliationName":[{"@value":"NTT Corporation,Japan"}]},{"@id":"https://cir.nii.ac.jp/crid/1380022497271473537","@type":"Researcher","foaf:name":[{"@value":"Keisuke Kinoshita"}],"jpcoar:affiliationName":[{"@value":"NTT Corporation,Japan"}]},{"@id":"https://cir.nii.ac.jp/crid/1380022497271473536","@type":"Researcher","foaf:name":[{"@value":"Rintaro Ikeshita"}],"jpcoar:affiliationName":[{"@value":"NTT Corporation,Japan"}]},{"@id":"https://cir.nii.ac.jp/crid/1380022497271473540","@type":"Researcher","foaf:name":[{"@value":"Shoko Araki"}],"jpcoar:affiliationName":[{"@value":"NTT Corporation,Japan"}]},{"@id":"https://cir.nii.ac.jp/crid/1380022497271473538","@type":"Researcher","foaf:name":[{"@value":"Hiroshi Sawada"}],"jpcoar:affiliationName":[{"@value":"NTT Corporation,Japan"}]}],"publication":{"prism:publicationName":[{"@value":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"}],"dc:publisher":[{"@value":"IEEE"}],"prism:publicationDate":"2021-06-06","prism:startingPage":"6129","prism:endingPage":"6133"},"reviewed":"false","dcterms:accessRights":"http://purl.org/coar/access_right/c_abf2","dc:rights":["https://doi.org/10.15223/policy-029","https://doi.org/10.15223/policy-037"],"url":[{"@id":"http://xplorestaging.ieee.org/ielx7/9413349/9413350/09414264.pdf?arnumber=9414264"}],"createdAt":"2021-05-13","modifiedAt":"2022-08-03","foaf:topic":[{"@id":"https://cir.nii.ac.jp/all?q=Signal%20Processing%20(eess.SP)","dc:title":"Signal Processing (eess.SP)"},{"@id":"https://cir.nii.ac.jp/all?q=FOS:%20Computer%20and%20information%20sciences","dc:title":"FOS: Computer and information sciences"},{"@id":"https://cir.nii.ac.jp/all?q=Sound%20(cs.SD)","dc:title":"Sound (cs.SD)"},{"@id":"https://cir.nii.ac.jp/all?q=Audio%20and%20Speech%20Processing%20(eess.AS)","dc:title":"Audio and Speech Processing (eess.AS)"},{"@id":"https://cir.nii.ac.jp/all?q=FOS:%20Electrical%20engineering,%20electronic%20engineering,%20information%20engineering","dc:title":"FOS: Electrical engineering, electronic engineering, information engineering"},{"@id":"https://cir.nii.ac.jp/all?q=Electrical%20Engineering%20and%20Systems%20Science%20-%20Signal%20Processing","dc:title":"Electrical Engineering and Systems Science - Signal Processing"},{"@id":"https://cir.nii.ac.jp/all?q=Computer%20Science%20-%20Sound","dc:title":"Computer Science - Sound"},{"@id":"https://cir.nii.ac.jp/all?q=Electrical%20Engineering%20and%20Systems%20Science%20-%20Audio%20and%20Speech%20Processing","dc:title":"Electrical Engineering and Systems Science - Audio and Speech Processing"}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360584340722947456","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@value":"Blind and Spatially-Regularized Online Joint Optimization of Source Separation, Dereverberation, and Noise Reduction"}]},{"@id":"https://cir.nii.ac.jp/crid/1390866647407670016","@type":"Article","relationType":["isReferencedBy"],"jpcoar:relatedTitle":[{"@language":"ja","@value":"混ざった声を聞き分ける最新技術：音源分離と目的音声抽出"},{"@language":"en","@value":"Listening to Speech in Mixture: Advances in Source Separation and Target Speech Extraction"}]}],"dataSourceIdentifier":[{"@type":"CROSSREF","@value":"10.1109/icassp39728.2021.9414264"},{"@type":"OPENAIRE","@value":"doi_dedup___::777963421491ef3dc9bb229c13bedc03"},{"@type":"CROSSREF","@value":"10.1109/taslp.2024.3351353_references_DOI_Ti4V6DzKcD1xOWvv1pjoqZYZPCI"},{"@type":"CROSSREF","@value":"10.1587/essfr.18.4_267_references_DOI_Ti4V6DzKcD1xOWvv1pjoqZYZPCI"}]}