Matches in SemOpenAlex for { <https://semopenalex.org/work/W3092097195> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3092097195 endingPage "5751" @default.
- W3092097195 startingPage "5751" @default.
- W3092097195 abstract "This paper proposes a novel technique to improve a spectral statistical filter for speech enhancement, to be applied in wearable hearing devices such as hearing aids. The proposed method is implemented considering a 32-channel uniform polyphase discrete Fourier transform filter bank, for which the overall algorithm processing delay is 8 ms in accordance with the hearing device requirements. The proposed speech enhancement technique, which exploits the concepts of both non-negative sparse coding (NNSC) and spectral statistical filtering, provides an online unified framework to overcome the problem of residual noise in spectral statistical filters under noisy environments. First, the spectral gain attenuator of the statistical Wiener filter is obtained using the a priori signal-to-noise ratio (SNR) estimated through a decision-directed approach. Next, the spectrum estimated using the Wiener spectral gain attenuator is decomposed by applying the NNSC technique to the target speech and residual noise components. These components are used to develop an NNSC-based Wiener spectral gain attenuator to achieve enhanced speech. The performance of the proposed NNSC–Wiener filter was evaluated through a perceptual evaluation of the speech quality scores under various noise conditions with SNRs ranging from -5 to 20 dB. The results indicated that the proposed NNSC–Wiener filter can outperform the conventional Wiener filter and NNSC-based speech enhancement methods at all SNRs." @default.
- W3092097195 created "2020-10-15" @default.
- W3092097195 creator A5084972635 @default.
- W3092097195 date "2020-10-10" @default.
- W3092097195 modified "2023-10-14" @default.
- W3092097195 title "Wearable Hearing Device Spectral Enhancement Driven by Non-Negative Sparse Coding-Based Residual Noise Reduction" @default.
- W3092097195 cites W1972316063 @default.
- W3092097195 cites W1974387177 @default.
- W3092097195 cites W1997650632 @default.
- W3092097195 cites W2000847282 @default.
- W3092097195 cites W2013608223 @default.
- W3092097195 cites W2029880715 @default.
- W3092097195 cites W2041063221 @default.
- W3092097195 cites W2049776357 @default.
- W3092097195 cites W2057200980 @default.
- W3092097195 cites W2062461584 @default.
- W3092097195 cites W2121086939 @default.
- W3092097195 cites W2133687299 @default.
- W3092097195 cites W2142083358 @default.
- W3092097195 cites W2157242178 @default.
- W3092097195 cites W2317830494 @default.
- W3092097195 cites W2335084046 @default.
- W3092097195 cites W2382519751 @default.
- W3092097195 cites W2772897972 @default.
- W3092097195 cites W2910778426 @default.
- W3092097195 cites W2952979007 @default.
- W3092097195 cites W2962866211 @default.
- W3092097195 cites W2972637927 @default.
- W3092097195 doi "https://doi.org/10.3390/s20205751" @default.
- W3092097195 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7600179" @default.
- W3092097195 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/33050447" @default.
- W3092097195 hasPublicationYear "2020" @default.
- W3092097195 type Work @default.
- W3092097195 sameAs 3092097195 @default.
- W3092097195 citedByCount "2" @default.
- W3092097195 countsByYear W30920971952022 @default.
- W3092097195 crossrefType "journal-article" @default.
- W3092097195 hasAuthorship W3092097195A5084972635 @default.
- W3092097195 hasBestOaLocation W30920971951 @default.
- W3092097195 hasConcept C11413529 @default.
- W3092097195 hasConcept C127413603 @default.
- W3092097195 hasConcept C154945302 @default.
- W3092097195 hasConcept C155512373 @default.
- W3092097195 hasConcept C15652857 @default.
- W3092097195 hasConcept C163294075 @default.
- W3092097195 hasConcept C174576160 @default.
- W3092097195 hasConcept C18537770 @default.
- W3092097195 hasConcept C24326235 @default.
- W3092097195 hasConcept C2776182073 @default.
- W3092097195 hasConcept C28490314 @default.
- W3092097195 hasConcept C29265498 @default.
- W3092097195 hasConcept C30044814 @default.
- W3092097195 hasConcept C41008148 @default.
- W3092097195 hasConceptScore W3092097195C11413529 @default.
- W3092097195 hasConceptScore W3092097195C127413603 @default.
- W3092097195 hasConceptScore W3092097195C154945302 @default.
- W3092097195 hasConceptScore W3092097195C155512373 @default.
- W3092097195 hasConceptScore W3092097195C15652857 @default.
- W3092097195 hasConceptScore W3092097195C163294075 @default.
- W3092097195 hasConceptScore W3092097195C174576160 @default.
- W3092097195 hasConceptScore W3092097195C18537770 @default.
- W3092097195 hasConceptScore W3092097195C24326235 @default.
- W3092097195 hasConceptScore W3092097195C2776182073 @default.
- W3092097195 hasConceptScore W3092097195C28490314 @default.
- W3092097195 hasConceptScore W3092097195C29265498 @default.
- W3092097195 hasConceptScore W3092097195C30044814 @default.
- W3092097195 hasConceptScore W3092097195C41008148 @default.
- W3092097195 hasFunder F4320322120 @default.
- W3092097195 hasIssue "20" @default.
- W3092097195 hasLocation W30920971951 @default.
- W3092097195 hasLocation W30920971952 @default.
- W3092097195 hasLocation W30920971953 @default.
- W3092097195 hasLocation W30920971954 @default.
- W3092097195 hasOpenAccess W3092097195 @default.
- W3092097195 hasPrimaryLocation W30920971951 @default.
- W3092097195 hasRelatedWork W1567734953 @default.
- W3092097195 hasRelatedWork W172871796 @default.
- W3092097195 hasRelatedWork W185494516 @default.
- W3092097195 hasRelatedWork W2045634261 @default.
- W3092097195 hasRelatedWork W2072441497 @default.
- W3092097195 hasRelatedWork W2118579084 @default.
- W3092097195 hasRelatedWork W2136606210 @default.
- W3092097195 hasRelatedWork W2151542770 @default.
- W3092097195 hasRelatedWork W2396333194 @default.
- W3092097195 hasRelatedWork W4375869276 @default.
- W3092097195 hasVolume "20" @default.
- W3092097195 isParatext "false" @default.
- W3092097195 isRetracted "false" @default.
- W3092097195 magId "3092097195" @default.
- W3092097195 workType "article" @default.