FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2765164841> ?p ?o ?g. }

• W2765164841 endingPage "25554" @default.
• W2765164841 startingPage "25542" @default.
• W2765164841 abstract "In wireless telephony and audio data mining applications, it is desirable that noise suppression can be made robust against changing noise conditions and operates in real time (or faster). The learning effectiveness and speed of artificial neural networks are therefore critical factors in applications for speech enhancement tasks. To address these issues, we present an extreme learning machine (ELM) framework, aimed at the effective and fast removal of background noise from a single-channel speech signal, based on a set of randomly chosen hidden units and analytically determined output weights. Because feature learning with shallow ELM may not be effective for natural signals, such as speech, even with a large number of hidden nodes, hierarchical ELM (H-ELM) architectures are deployed by leveraging sparse autoencoders. In this manner, we not only keep all the advantages of deep models in approximating complicated functions and maintaining strong regression capabilities, but we also overcome the cumbersome and time-consuming features of both greedy layer-wise pre-training and back-propagation (BP)-based fine tuning schemes, which are typically adopted for training deep neural architectures. The proposed ELM framework was evaluated on the Aurora-4 speech database. The Aurora-4 task provides relatively limited training data, and test speech data corrupted with both additive noise and convolutive distortions for matched and mismatched channels and signal-to-noise ratio (SNR) conditions. In addition, the task includes a subset of testing data involving noise types and SNR levels that are not seen in the training data. The experimental results indicate that when the amount of training data is limited, both ELMand H-ELM-based speech enhancement techniques consistently outperform the conventional BP-based shallow and deep learning algorithms, in terms of standardized objective evaluations, under various testing conditions." @default.
• W2765164841 created "2017-11-10" @default.
• W2765164841 creator A5005486605 @default.
• W2765164841 creator A5044008055 @default.
• W2765164841 creator A5073046122 @default.
• W2765164841 creator A5079659476 @default.
• W2765164841 creator A5086107623 @default.
• W2765164841 creator A5089443958 @default.
• W2765164841 date "2017-01-01" @default.
• W2765164841 modified "2023-09-26" @default.
• W2765164841 title "Experimental Study on Extreme Learning Machine Applications for Speech Enhancement" @default.
• W2765164841 cites W1538759723 @default.
• W2765164841 cites W1964509438 @default.
• W2765164841 cites W1966264494 @default.
• W2765164841 cites W1975301756 @default.
• W2765164841 cites W1995436378 @default.
• W2765164841 cites W1999977067 @default.
• W2765164841 cites W2012642013 @default.
• W2765164841 cites W2021355302 @default.
• W2765164841 cites W2026131661 @default.
• W2765164841 cites W2044893557 @default.
• W2765164841 cites W2075731813 @default.
• W2765164841 cites W2100495367 @default.
• W2765164841 cites W2100556411 @default.
• W2765164841 cites W2105594594 @default.
• W2765164841 cites W2109349638 @default.
• W2765164841 cites W2111072639 @default.
• W2765164841 cites W2116756305 @default.
• W2765164841 cites W2130476329 @default.
• W2765164841 cites W2138456300 @default.
• W2765164841 cites W2141695047 @default.
• W2765164841 cites W2141998673 @default.
• W2765164841 cites W2145760110 @default.
• W2765164841 cites W2153894152 @default.
• W2765164841 cites W2158113823 @default.
• W2765164841 cites W2163101527 @default.
• W2765164841 cites W2163683764 @default.
• W2765164841 cites W2164764235 @default.
• W2765164841 cites W2168379380 @default.
• W2765164841 cites W2188644438 @default.
• W2765164841 cites W2221512005 @default.
• W2765164841 cites W2244918895 @default.
• W2765164841 cites W2301541953 @default.
• W2765164841 cites W2317354861 @default.
• W2765164841 cites W2326115863 @default.
• W2765164841 cites W2328191957 @default.
• W2765164841 cites W2343893516 @default.
• W2765164841 cites W2489547515 @default.
• W2765164841 cites W2518926167 @default.
• W2765164841 cites W2527611302 @default.
• W2765164841 cites W2531174837 @default.
• W2765164841 cites W2562555919 @default.
• W2765164841 cites W2584393883 @default.
• W2765164841 cites W2591940486 @default.
• W2765164841 cites W3147539069 @default.
• W2765164841 cites W4253928870 @default.
• W2765164841 doi "https://doi.org/10.1109/access.2017.2766675" @default.
• W2765164841 hasPublicationYear "2017" @default.
• W2765164841 type Work @default.
• W2765164841 sameAs 2765164841 @default.
• W2765164841 citedByCount "38" @default.
• W2765164841 countsByYear W27651648412018 @default.
• W2765164841 countsByYear W27651648412019 @default.
• W2765164841 countsByYear W27651648412020 @default.
• W2765164841 countsByYear W27651648412021 @default.
• W2765164841 countsByYear W27651648412022 @default.
• W2765164841 countsByYear W27651648412023 @default.
• W2765164841 crossrefType "journal-article" @default.
• W2765164841 hasAuthorship W2765164841A5005486605 @default.
• W2765164841 hasAuthorship W2765164841A5044008055 @default.
• W2765164841 hasAuthorship W2765164841A5073046122 @default.
• W2765164841 hasAuthorship W2765164841A5079659476 @default.
• W2765164841 hasAuthorship W2765164841A5086107623 @default.
• W2765164841 hasAuthorship W2765164841A5089443958 @default.
• W2765164841 hasBestOaLocation W27651648411 @default.
• W2765164841 hasConcept C108583219 @default.
• W2765164841 hasConcept C115961682 @default.
• W2765164841 hasConcept C119857082 @default.
• W2765164841 hasConcept C127162648 @default.
• W2765164841 hasConcept C153180895 @default.
• W2765164841 hasConcept C154945302 @default.
• W2765164841 hasConcept C162324750 @default.
• W2765164841 hasConcept C163294075 @default.
• W2765164841 hasConcept C187736073 @default.
• W2765164841 hasConcept C2776182073 @default.
• W2765164841 hasConcept C2780150128 @default.
• W2765164841 hasConcept C2780451532 @default.
• W2765164841 hasConcept C28490314 @default.
• W2765164841 hasConcept C41008148 @default.
• W2765164841 hasConcept C50644808 @default.
• W2765164841 hasConcept C76155785 @default.
• W2765164841 hasConcept C99498987 @default.
• W2765164841 hasConceptScore W2765164841C108583219 @default.
• W2765164841 hasConceptScore W2765164841C115961682 @default.
• W2765164841 hasConceptScore W2765164841C119857082 @default.
• W2765164841 hasConceptScore W2765164841C127162648 @default.
• W2765164841 hasConceptScore W2765164841C153180895 @default.
• W2765164841 hasConceptScore W2765164841C154945302 @default.

• next