FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2897977894> ?p ?o ?g. }

• W2897977894 endingPage "188" @default.
• W2897977894 startingPage "178" @default.
• W2897977894 abstract "Deep learning-based time-frequency T-F masking has dramatically advanced monaural single-channel speech separation and enhancement. This study investigates its potential for direction of arrival DOA estimation in noisy and reverberant environments. We explore ways of combining T-F masking and conventional localization algorithms, such as generalized cross correlation with phase transform, as well as newly proposed algorithms based on steered-response SNR and steering vectors. The key idea is to utilize deep neural networks DNNs to identify speech dominant T-F units containing relatively clean phase for DOA estimation. Our DNN is trained using only monaural spectral information, and this makes the trained model directly applicable to arrays with various numbers of microphones arranged in diverse geometries. Although only monaural information is used for training, experimental results show strong robustness of the proposed approach in new environments with intense noise and room reverberation, outperforming traditional DOA estimation methods by large margins. Our study also suggests that the ideal ratio mask and its variants remain effective training targets for robust speaker localization." @default.
• W2897977894 created "2018-10-26" @default.
• W2897977894 creator A5022772351 @default.
• W2897977894 creator A5045708462 @default.
• W2897977894 creator A5051837453 @default.
• W2897977894 date "2019-01-01" @default.
• W2897977894 modified "2023-10-12" @default.
• W2897977894 title "Robust Speaker Localization Guided by Deep Learning-Based Time-Frequency Masking" @default.
• W2897977894 cites W1482149378 @default.
• W2897977894 cites W1516630152 @default.
• W2897977894 cites W1555217905 @default.
• W2897977894 cites W1562552815 @default.
• W2897977894 cites W1603075283 @default.
• W2897977894 cites W160800111 @default.
• W2897977894 cites W1964998538 @default.
• W2897977894 cites W1971405469 @default.
• W2897977894 cites W1993678034 @default.
• W2897977894 cites W1996304098 @default.
• W2897977894 cites W2034040413 @default.
• W2897977894 cites W2046317813 @default.
• W2897977894 cites W2056522351 @default.
• W2897977894 cites W2064675550 @default.
• W2897977894 cites W2069681747 @default.
• W2897977894 cites W2093010905 @default.
• W2897977894 cites W2100818340 @default.
• W2897977894 cites W2104422351 @default.
• W2897977894 cites W2113638573 @default.
• W2897977894 cites W2113679114 @default.
• W2897977894 cites W2136484266 @default.
• W2897977894 cites W2148613904 @default.
• W2897977894 cites W2150384167 @default.
• W2897977894 cites W2155323221 @default.
• W2897977894 cites W2168379380 @default.
• W2897977894 cites W2218753925 @default.
• W2897977894 cites W2288645994 @default.
• W2897977894 cites W2289394825 @default.
• W2897977894 cites W2289480995 @default.
• W2897977894 cites W2291877678 @default.
• W2897977894 cites W2364134690 @default.
• W2897977894 cites W2533459608 @default.
• W2897977894 cites W2559260703 @default.
• W2897977894 cites W2568308529 @default.
• W2897977894 cites W2611943505 @default.
• W2897977894 cites W2678916739 @default.
• W2897977894 cites W2698117193 @default.
• W2897977894 cites W2701869962 @default.
• W2897977894 cites W2718052359 @default.
• W2897977894 cites W2765962757 @default.
• W2897977894 cites W2773475413 @default.
• W2897977894 cites W2962708126 @default.
• W2897977894 cites W2962866211 @default.
• W2897977894 cites W4256399001 @default.
• W2897977894 doi "https://doi.org/10.1109/taslp.2018.2876169" @default.
• W2897977894 hasPublicationYear "2019" @default.
• W2897977894 type Work @default.
• W2897977894 sameAs 2897977894 @default.
• W2897977894 citedByCount "80" @default.
• W2897977894 countsByYear W28979778942018 @default.
• W2897977894 countsByYear W28979778942019 @default.
• W2897977894 countsByYear W28979778942020 @default.
• W2897977894 countsByYear W28979778942021 @default.
• W2897977894 countsByYear W28979778942022 @default.
• W2897977894 countsByYear W28979778942023 @default.
• W2897977894 crossrefType "journal-article" @default.
• W2897977894 hasAuthorship W2897977894A5022772351 @default.
• W2897977894 hasAuthorship W2897977894A5045708462 @default.
• W2897977894 hasAuthorship W2897977894A5051837453 @default.
• W2897977894 hasBestOaLocation W28979778941 @default.
• W2897977894 hasConcept C106131492 @default.
• W2897977894 hasConcept C133892786 @default.
• W2897977894 hasConcept C142362112 @default.
• W2897977894 hasConcept C142433447 @default.
• W2897977894 hasConcept C153349607 @default.
• W2897977894 hasConcept C154945302 @default.
• W2897977894 hasConcept C2777402240 @default.
• W2897977894 hasConcept C28490314 @default.
• W2897977894 hasConcept C2982762665 @default.
• W2897977894 hasConcept C31972630 @default.
• W2897977894 hasConcept C41008148 @default.
• W2897977894 hasConceptScore W2897977894C106131492 @default.
• W2897977894 hasConceptScore W2897977894C133892786 @default.
• W2897977894 hasConceptScore W2897977894C142362112 @default.
• W2897977894 hasConceptScore W2897977894C142433447 @default.
• W2897977894 hasConceptScore W2897977894C153349607 @default.
• W2897977894 hasConceptScore W2897977894C154945302 @default.
• W2897977894 hasConceptScore W2897977894C2777402240 @default.
• W2897977894 hasConceptScore W2897977894C28490314 @default.
• W2897977894 hasConceptScore W2897977894C2982762665 @default.
• W2897977894 hasConceptScore W2897977894C31972630 @default.
• W2897977894 hasConceptScore W2897977894C41008148 @default.
• W2897977894 hasFunder F4320306076 @default.
• W2897977894 hasFunder F4320338294 @default.
• W2897977894 hasIssue "1" @default.
• W2897977894 hasLocation W28979778941 @default.
• W2897977894 hasOpenAccess W2897977894 @default.
• W2897977894 hasPrimaryLocation W28979778941 @default.
• W2897977894 hasRelatedWork W1516392727 @default.
• W2897977894 hasRelatedWork W1585307611 @default.

• next