{"@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/1360021390582771968.json","@type":"Article","productIdentifier":[{"identifier":{"@type":"DOI","@value":"10.1109/icassp49357.2023.10096128"}},{"identifier":{"@type":"URI","@value":"http://xplorestaging.ieee.org/ielx7/10094559/10094560/10096128.pdf?arnumber=10096128"}}],"resourceType":"学術雑誌論文(journal article)","dc:title":[{"@value":"Self-Adaptive Incremental Machine Speech Chain for Lombard TTS with High-Granularity ASR Feedback in Dynamic Noise Condition"}],"creator":[{"@id":"https://cir.nii.ac.jp/crid/1380021390582771973","@type":"Researcher","foaf:name":[{"@value":"Sashi Novitasari"}],"jpcoar:affiliationName":[{"@value":"Nara Institute of Science and Technology,Japan"}]},{"@id":"https://cir.nii.ac.jp/crid/1420285329315650816","@type":"Researcher","personIdentifier":[{"@type":"KAKEN_RESEARCHERS","@value":"00395005"},{"@type":"NRID","@value":"1000000395005"},{"@type":"NRID","@value":"9000413895381"},{"@type":"NRID","@value":"9000410926841"},{"@type":"NRID","@value":"9000414516811"},{"@type":"RESEARCHMAP","@value":"https://researchmap.jp/ssakti"}],"foaf:name":[{"@value":"Sakriani Sakti"}],"jpcoar:affiliationName":[{"@value":"Japan Advanced Institute of Science and Technology,Japan"}]},{"@id":"https://cir.nii.ac.jp/crid/1380021390582771969","@type":"Researcher","foaf:name":[{"@value":"Satoshi Nakamura"}],"jpcoar:affiliationName":[{"@value":"Nara Institute of Science and Technology,Japan"}]}],"publication":{"prism:publicationName":[{"@value":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"}],"dc:publisher":[{"@value":"IEEE"}],"prism:publicationDate":"2023-06-04","prism:startingPage":"1","prism:endingPage":"5"},"reviewed":"false","dc:rights":["https://doi.org/10.15223/policy-029","https://doi.org/10.15223/policy-037"],"url":[{"@id":"http://xplorestaging.ieee.org/ielx7/10094559/10094560/10096128.pdf?arnumber=10096128"}],"createdAt":"2023-05-05","modifiedAt":"2023-11-20","project":[{"@id":"https://cir.nii.ac.jp/crid/1040862776831614848","@type":"Project","projectIdentifier":[{"@type":"KAKEN","@value":"23K21681"},{"@type":"JGN","@value":"JP23K21681"},{"@type":"URI","@value":"https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-23K21681/"}],"notation":[{"@language":"ja","@value":"言語の壁を超える低資源多言語Machine Speech Chain技術の構築"},{"@language":"en","@value":"Developing Low-Resource Multilingual Machine Speech Chain for Breaking Language Barriers"}]}],"relatedProduct":[{"@id":"https://cir.nii.ac.jp/crid/1360017286008048768","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Enhancing Speech Intelligibility in Text-To-Speech Synthesis Using Speaking Style Conversion"}]},{"@id":"https://cir.nii.ac.jp/crid/1360292620102402944","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Speech-Transformer: A No-Recurrence Sequence-to-Sequence Model for Speech Recognition"}]},{"@id":"https://cir.nii.ac.jp/crid/1360294646531408000","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Analysis of HMM-based lombard speech synthesis"}]},{"@id":"https://cir.nii.ac.jp/crid/1360580238252882560","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Intelligibility-enhancing speech modifications: the hurricane challenge"}]},{"@id":"https://cir.nii.ac.jp/crid/1360580238252896128","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"MultiSpeech: Multi-Speaker Text to Speech with Transformer"}]},{"@id":"https://cir.nii.ac.jp/crid/1360584346107711616","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Semi-Supervision in ASR: Sequential MixMatch and Factorized TTS-Based Augmentation"}]},{"@id":"https://cir.nii.ac.jp/crid/1360848660087015168","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Listening while speaking: Speech chain by deep learning"}]},{"@id":"https://cir.nii.ac.jp/crid/1360857593802076032","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Dynamically Adaptive Machine Speech Chain Inference for TTS in Noisy Environment: Listen and Speak Louder"}]},{"@id":"https://cir.nii.ac.jp/crid/1360861705597871488","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"A Machine Speech Chain Approach for Dynamically Adaptive Lombard TTS in Static and Dynamic Noise Environments"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137044246407680","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Semi-supervised End-to-end Speech Recognition Using Text-to-speech and Autoencoders"}]},{"@id":"https://cir.nii.ac.jp/crid/1361137044389522816","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The Lombard Sign and the Role of Hearing in Speech"}]},{"@id":"https://cir.nii.ac.jp/crid/1361694370246436736","@type":"Article","resourceType":"学術雑誌論文(journal article)","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Machine Speech Chain"}]},{"@id":"https://cir.nii.ac.jp/crid/1362825895726655232","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Speech Recognition with Augmented Synthesized Speech"}]},{"@id":"https://cir.nii.ac.jp/crid/1363107371267307776","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"The design for the wall street journal-based CSR corpus"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951793330379904","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Influence of Sound Immersion and Communicative Interaction on the Lombard Effect"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951793761920384","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Tacotron: Towards End-to-End Speech Synthesis"}]},{"@id":"https://cir.nii.ac.jp/crid/1363951794284126720","@type":"Article","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"An Algorithm for Intelligibility Prediction of Time–Frequency Weighted Noisy Speech"}]},{"@id":"https://cir.nii.ac.jp/crid/1370021390582771979","@type":"Product","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"FastSpeech 2: Fast and high-quality end-to-end text to speech"}]},{"@id":"https://cir.nii.ac.jp/crid/1370021390582771981","@type":"Product","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"Hurricane natural speech corpus, [sound]"}]},{"@id":"https://cir.nii.ac.jp/crid/1370021390582771982","@type":"Product","relationType":["references"],"jpcoar:relatedTitle":[{"@value":"FastSpeech: Fast, robust and controllable text to speech"}]}],"dataSourceIdentifier":[{"@type":"CROSSREF","@value":"10.1109/icassp49357.2023.10096128"},{"@type":"KAKEN","@value":"PRODUCT-25258195"},{"@type":"OPENAIRE","@value":"doi_________::a1d9e8618aae4e5af992e9cabd961144"}]}