FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312918084> ?p ?o ?g. }

• W4312918084 endingPage "683" @default.
• W4312918084 startingPage "670" @default.
• W4312918084 abstract "This work addresses the problem of 3D-localizing and enhancing the speech of one main speaker in noisy multi-speaker hospital environments using a multi-channel microphone array. In our model, we propose conducting speaker localization using a machine learning model based on convolutional recurrent neural networks (CRNN) followed by minimum variance distortionless response (MVDR) beamforming. In addition, to ensure that our speech enhancement module is adaptive when deployed in different environments, we trained a meta learning model. Firstly, in the localization step, an estimation of the direction of arrival (DOA) in the elevation and azimuth planes is executed. This is conducted in a 3D space with the presence of noise, reverberation, and up to two more speakers. Using estimated DOA, the MVDR beamformer then enhances the speech of the main speaker. In order to test our model, we adopted and simulated a real-world problem where the objective was to enhance the speech of a clinician in a noisy intensive care unit (ICU) with the presence of other speakers. Furthermore, in order to validate our model, we adopted a speech-to-text module to evaluate the word error rate. Moreover, we implemented our algorithm on hardware using commercially available components and tested it in a real environment. Results showed that our model outperforms other machine learning and non-machine learning algorithms. Finally, we used our trained Meta Learning model to show that our model can adapt to new environments while maintaining high performance after retraining with only a few-shot recordings." @default.
• W4312918084 created "2023-01-05" @default.
• W4312918084 creator A5003503441 @default.
• W4312918084 creator A5020505546 @default.
• W4312918084 creator A5028312507 @default.
• W4312918084 creator A5028509717 @default.
• W4312918084 creator A5057966799 @default.
• W4312918084 date "2023-01-01" @default.
• W4312918084 modified "2023-10-05" @default.
• W4312918084 title "Localization-Driven Speech Enhancement in Noisy Multi-Speaker Hospital Environments Using Deep Learning and Meta Learning" @default.
• W4312918084 cites W1603075283 @default.
• W4312918084 cites W2018541726 @default.
• W4312918084 cites W2066218102 @default.
• W4312918084 cites W2113638573 @default.
• W4312918084 cites W2113744809 @default.
• W4312918084 cites W2117678320 @default.
• W4312918084 cites W2144244295 @default.
• W4312918084 cites W2145680191 @default.
• W4312918084 cites W2551990143 @default.
• W4312918084 cites W2586642235 @default.
• W4312918084 cites W2611943505 @default.
• W4312918084 cites W2772736377 @default.
• W4312918084 cites W2810934215 @default.
• W4312918084 cites W2885219692 @default.
• W4312918084 cites W2914926710 @default.
• W4312918084 cites W2962708126 @default.
• W4312918084 cites W2962999716 @default.
• W4312918084 cites W2963070905 @default.
• W4312918084 cites W2964316912 @default.
• W4312918084 cites W2964342924 @default.
• W4312918084 cites W2985698910 @default.
• W4312918084 cites W3009685637 @default.
• W4312918084 cites W3015474227 @default.
• W4312918084 cites W3104947433 @default.
• W4312918084 cites W38194800 @default.
• W4312918084 doi "https://doi.org/10.1109/taslp.2022.3231700" @default.
• W4312918084 hasPublicationYear "2023" @default.
• W4312918084 type Work @default.
• W4312918084 citedByCount "3" @default.
• W4312918084 countsByYear W43129180842023 @default.
• W4312918084 crossrefType "journal-article" @default.
• W4312918084 hasAuthorship W4312918084A5003503441 @default.
• W4312918084 hasAuthorship W4312918084A5020505546 @default.
• W4312918084 hasAuthorship W4312918084A5028312507 @default.
• W4312918084 hasAuthorship W4312918084A5028509717 @default.
• W4312918084 hasAuthorship W4312918084A5057966799 @default.
• W4312918084 hasConcept C108583219 @default.
• W4312918084 hasConcept C115961682 @default.
• W4312918084 hasConcept C119599485 @default.
• W4312918084 hasConcept C127413603 @default.
• W4312918084 hasConcept C153180895 @default.
• W4312918084 hasConcept C154945302 @default.
• W4312918084 hasConcept C163294075 @default.
• W4312918084 hasConcept C2776182073 @default.
• W4312918084 hasConcept C2778263558 @default.
• W4312918084 hasConcept C2778806681 @default.
• W4312918084 hasConcept C28490314 @default.
• W4312918084 hasConcept C40969351 @default.
• W4312918084 hasConcept C41008148 @default.
• W4312918084 hasConcept C54197355 @default.
• W4312918084 hasConcept C68115822 @default.
• W4312918084 hasConcept C76155785 @default.
• W4312918084 hasConcept C81363708 @default.
• W4312918084 hasConcept C95851461 @default.
• W4312918084 hasConcept C99498987 @default.
• W4312918084 hasConceptScore W4312918084C108583219 @default.
• W4312918084 hasConceptScore W4312918084C115961682 @default.
• W4312918084 hasConceptScore W4312918084C119599485 @default.
• W4312918084 hasConceptScore W4312918084C127413603 @default.
• W4312918084 hasConceptScore W4312918084C153180895 @default.
• W4312918084 hasConceptScore W4312918084C154945302 @default.
• W4312918084 hasConceptScore W4312918084C163294075 @default.
• W4312918084 hasConceptScore W4312918084C2776182073 @default.
• W4312918084 hasConceptScore W4312918084C2778263558 @default.
• W4312918084 hasConceptScore W4312918084C2778806681 @default.
• W4312918084 hasConceptScore W4312918084C28490314 @default.
• W4312918084 hasConceptScore W4312918084C40969351 @default.
• W4312918084 hasConceptScore W4312918084C41008148 @default.
• W4312918084 hasConceptScore W4312918084C54197355 @default.
• W4312918084 hasConceptScore W4312918084C68115822 @default.
• W4312918084 hasConceptScore W4312918084C76155785 @default.
• W4312918084 hasConceptScore W4312918084C81363708 @default.
• W4312918084 hasConceptScore W4312918084C95851461 @default.
• W4312918084 hasConceptScore W4312918084C99498987 @default.
• W4312918084 hasLocation W43129180841 @default.
• W4312918084 hasOpenAccess W4312918084 @default.
• W4312918084 hasPrimaryLocation W43129180841 @default.
• W4312918084 hasRelatedWork W1126203183 @default.
• W4312918084 hasRelatedWork W1135071008 @default.
• W4312918084 hasRelatedWork W1491017269 @default.
• W4312918084 hasRelatedWork W154138180 @default.
• W4312918084 hasRelatedWork W2047990629 @default.
• W4312918084 hasRelatedWork W2127095651 @default.
• W4312918084 hasRelatedWork W2155276444 @default.
• W4312918084 hasRelatedWork W2161947961 @default.
• W4312918084 hasRelatedWork W2185164075 @default.
• W4312918084 hasRelatedWork W75021890 @default.
• W4312918084 hasVolume "31" @default.

• next