Matches in SemOpenAlex for { <https://semopenalex.org/work/W3192559547> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W3192559547 abstract "Speech processing is an important application area of digital signal processing that helps examine and analyze the speech signal. In this processing, speech enhancement is an essential factor because it improves the quality of the signal that helps resolve the communication challenges. Different speech enhancement algorithms are utilized in the research field, but limited processing capabilities, maximum microphone distance, and voice-first I.O. interfaces create the computation complexity. In this paper, speech enhancement is done in two steps. In an initial step, spectral subtraction method is applied to LJ Speech dataset. In the first stage, noise spectrum is estimated during pauses and it is subtracted from the noisy speech signal to obtain the clean speech signal. However, spectral subtraction method still introduces artificial noise and narrow-band noise in the spectrum. Hence, artificial bandwidth expansion with a deep shallow convolution neural network (ABE-DSCNN) is implemented as a second stage in the paper. Further, developed system is compared with conventional enhancement approaches such as deep learning network (DNN), neural beam forming (NB) and generative adversarial network (GAN). The experimental results show that an ABS-DSCNN provides 4% increase of PSEQ and error rate improved by 40% to 56% with respect to the other existing algorithms for 1000 speech samples. Hence, the paper concludes that ABE-DSCNN approach effectively improves the speech quality." @default.
- W3192559547 created "2021-08-16" @default.
- W3192559547 creator A5010916041 @default.
- W3192559547 creator A5023060699 @default.
- W3192559547 creator A5071200348 @default.
- W3192559547 date "2021-07-30" @default.
- W3192559547 modified "2023-09-26" @default.
- W3192559547 title "Enhancing Speech Quality Using Artificial Bandwidth Expansion with Deep Shallow Convolution Neural Network Framework" @default.
- W3192559547 cites W1817183475 @default.
- W3192559547 cites W1968939597 @default.
- W3192559547 cites W1972312031 @default.
- W3192559547 cites W1989034586 @default.
- W3192559547 cites W1999846783 @default.
- W3192559547 cites W2096779346 @default.
- W3192559547 cites W2121973264 @default.
- W3192559547 cites W2128653836 @default.
- W3192559547 cites W2140977001 @default.
- W3192559547 cites W2150678273 @default.
- W3192559547 cites W2154066856 @default.
- W3192559547 cites W2166117654 @default.
- W3192559547 cites W2520273967 @default.
- W3192559547 cites W2545456137 @default.
- W3192559547 cites W2609317876 @default.
- W3192559547 cites W2733394600 @default.
- W3192559547 cites W2766719746 @default.
- W3192559547 cites W2802304149 @default.
- W3192559547 cites W2884943196 @default.
- W3192559547 cites W2953726307 @default.
- W3192559547 cites W2962996339 @default.
- W3192559547 cites W2974481323 @default.
- W3192559547 cites W2998749473 @default.
- W3192559547 cites W3013018143 @default.
- W3192559547 cites W3039137888 @default.
- W3192559547 cites W3081889057 @default.
- W3192559547 cites W4252679093 @default.
- W3192559547 cites W46679383 @default.
- W3192559547 cites W2801695703 @default.
- W3192559547 doi "https://doi.org/10.1142/s0219477522500080" @default.
- W3192559547 hasPublicationYear "2021" @default.
- W3192559547 type Work @default.
- W3192559547 sameAs 3192559547 @default.
- W3192559547 citedByCount "2" @default.
- W3192559547 countsByYear W31925595472022 @default.
- W3192559547 countsByYear W31925595472023 @default.
- W3192559547 crossrefType "journal-article" @default.
- W3192559547 hasAuthorship W3192559547A5010916041 @default.
- W3192559547 hasAuthorship W3192559547A5023060699 @default.
- W3192559547 hasAuthorship W3192559547A5071200348 @default.
- W3192559547 hasConcept C108583219 @default.
- W3192559547 hasConcept C154945302 @default.
- W3192559547 hasConcept C163294075 @default.
- W3192559547 hasConcept C204201278 @default.
- W3192559547 hasConcept C2776182073 @default.
- W3192559547 hasConcept C2776257435 @default.
- W3192559547 hasConcept C2778263558 @default.
- W3192559547 hasConcept C28490314 @default.
- W3192559547 hasConcept C41008148 @default.
- W3192559547 hasConcept C50644808 @default.
- W3192559547 hasConcept C61328038 @default.
- W3192559547 hasConcept C68115822 @default.
- W3192559547 hasConcept C76155785 @default.
- W3192559547 hasConceptScore W3192559547C108583219 @default.
- W3192559547 hasConceptScore W3192559547C154945302 @default.
- W3192559547 hasConceptScore W3192559547C163294075 @default.
- W3192559547 hasConceptScore W3192559547C204201278 @default.
- W3192559547 hasConceptScore W3192559547C2776182073 @default.
- W3192559547 hasConceptScore W3192559547C2776257435 @default.
- W3192559547 hasConceptScore W3192559547C2778263558 @default.
- W3192559547 hasConceptScore W3192559547C28490314 @default.
- W3192559547 hasConceptScore W3192559547C41008148 @default.
- W3192559547 hasConceptScore W3192559547C50644808 @default.
- W3192559547 hasConceptScore W3192559547C61328038 @default.
- W3192559547 hasConceptScore W3192559547C68115822 @default.
- W3192559547 hasConceptScore W3192559547C76155785 @default.
- W3192559547 hasIssue "01" @default.
- W3192559547 hasLocation W31925595471 @default.
- W3192559547 hasOpenAccess W3192559547 @default.
- W3192559547 hasPrimaryLocation W31925595471 @default.
- W3192559547 hasRelatedWork W11553578 @default.
- W3192559547 hasRelatedWork W11880096 @default.
- W3192559547 hasRelatedWork W13343246 @default.
- W3192559547 hasRelatedWork W13920906 @default.
- W3192559547 hasRelatedWork W2433769 @default.
- W3192559547 hasRelatedWork W3974743 @default.
- W3192559547 hasRelatedWork W5835750 @default.
- W3192559547 hasRelatedWork W5939791 @default.
- W3192559547 hasRelatedWork W6304026 @default.
- W3192559547 hasRelatedWork W7958345 @default.
- W3192559547 hasVolume "21" @default.
- W3192559547 isParatext "false" @default.
- W3192559547 isRetracted "false" @default.
- W3192559547 magId "3192559547" @default.
- W3192559547 workType "article" @default.