Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783185598> ?p ?o ?g. }
- W2783185598 abstract "In this paper, we propose a method for post-processing of deep neural network (DNN) enhanced speech. The method, which is simple and does not require additional training or expansion of the feature or target vectors, can be viewed as a mask-based approach in which a noisy speech signal is processed by a time-frequency (T-F) weighting derived from the noise-free spectral estimate of a DNN. A series of experiments and statistical analyses of results are carried out to compare the performance of the proposed approach to a baseline DNN enhancement system that features no post processing. Objective tests show that the proposed approach always improves both speech quality and intelligibility, and it outperforms a corresponding baseline system in both matched and mismatched noise conditions. Analysis of the enhanced speech shows that post processing reduces severe amplification distortions in the magnitude spectrum of the enhanced speech at the cost of a slight increase in severe attenuation distortions." @default.
- W2783185598 created "2018-01-26" @default.
- W2783185598 creator A5033437141 @default.
- W2783185598 creator A5050801227 @default.
- W2783185598 date "2017-12-01" @default.
- W2783185598 modified "2023-09-25" @default.
- W2783185598 title "A Mask-Based Post Processing Approach for Improving the Quality and Intelligibility of Deep Neural Network Enhanced Speech" @default.
- W2783185598 cites W1495679096 @default.
- W2783185598 cites W1552314771 @default.
- W2783185598 cites W1604034532 @default.
- W2783185598 cites W1677182931 @default.
- W2783185598 cites W1897240248 @default.
- W2783185598 cites W1968939597 @default.
- W2783185598 cites W1979099822 @default.
- W2783185598 cites W1980741455 @default.
- W2783185598 cites W1988087240 @default.
- W2783185598 cites W1989034586 @default.
- W2783185598 cites W2035424729 @default.
- W2783185598 cites W2044893557 @default.
- W2783185598 cites W2055611715 @default.
- W2783185598 cites W2062164080 @default.
- W2783185598 cites W2067295501 @default.
- W2783185598 cites W2104189141 @default.
- W2783185598 cites W2121973264 @default.
- W2783185598 cites W2126942983 @default.
- W2783185598 cites W2128653836 @default.
- W2783185598 cites W2137613818 @default.
- W2783185598 cites W2141998673 @default.
- W2783185598 cites W2144404214 @default.
- W2783185598 cites W2156387975 @default.
- W2783185598 cites W2175872006 @default.
- W2783185598 cites W2318802957 @default.
- W2783185598 cites W2396130155 @default.
- W2783185598 cites W2397226255 @default.
- W2783185598 cites W2404892923 @default.
- W2783185598 cites W2405774341 @default.
- W2783185598 cites W2561557072 @default.
- W2783185598 doi "https://doi.org/10.1109/icmla.2017.00014" @default.
- W2783185598 hasPublicationYear "2017" @default.
- W2783185598 type Work @default.
- W2783185598 sameAs 2783185598 @default.
- W2783185598 citedByCount "0" @default.
- W2783185598 crossrefType "proceedings-article" @default.
- W2783185598 hasAuthorship W2783185598A5033437141 @default.
- W2783185598 hasAuthorship W2783185598A5050801227 @default.
- W2783185598 hasConcept C100675267 @default.
- W2783185598 hasConcept C104267543 @default.
- W2783185598 hasConcept C111472728 @default.
- W2783185598 hasConcept C121332964 @default.
- W2783185598 hasConcept C138885662 @default.
- W2783185598 hasConcept C153180895 @default.
- W2783185598 hasConcept C154945302 @default.
- W2783185598 hasConcept C163294075 @default.
- W2783185598 hasConcept C183115368 @default.
- W2783185598 hasConcept C204201278 @default.
- W2783185598 hasConcept C24890656 @default.
- W2783185598 hasConcept C2776182073 @default.
- W2783185598 hasConcept C28490314 @default.
- W2783185598 hasConcept C29265498 @default.
- W2783185598 hasConcept C41008148 @default.
- W2783185598 hasConcept C50644808 @default.
- W2783185598 hasConcept C554190296 @default.
- W2783185598 hasConcept C60048801 @default.
- W2783185598 hasConcept C61328038 @default.
- W2783185598 hasConcept C76155785 @default.
- W2783185598 hasConceptScore W2783185598C100675267 @default.
- W2783185598 hasConceptScore W2783185598C104267543 @default.
- W2783185598 hasConceptScore W2783185598C111472728 @default.
- W2783185598 hasConceptScore W2783185598C121332964 @default.
- W2783185598 hasConceptScore W2783185598C138885662 @default.
- W2783185598 hasConceptScore W2783185598C153180895 @default.
- W2783185598 hasConceptScore W2783185598C154945302 @default.
- W2783185598 hasConceptScore W2783185598C163294075 @default.
- W2783185598 hasConceptScore W2783185598C183115368 @default.
- W2783185598 hasConceptScore W2783185598C204201278 @default.
- W2783185598 hasConceptScore W2783185598C24890656 @default.
- W2783185598 hasConceptScore W2783185598C2776182073 @default.
- W2783185598 hasConceptScore W2783185598C28490314 @default.
- W2783185598 hasConceptScore W2783185598C29265498 @default.
- W2783185598 hasConceptScore W2783185598C41008148 @default.
- W2783185598 hasConceptScore W2783185598C50644808 @default.
- W2783185598 hasConceptScore W2783185598C554190296 @default.
- W2783185598 hasConceptScore W2783185598C60048801 @default.
- W2783185598 hasConceptScore W2783185598C61328038 @default.
- W2783185598 hasConceptScore W2783185598C76155785 @default.
- W2783185598 hasLocation W27831855981 @default.
- W2783185598 hasOpenAccess W2783185598 @default.
- W2783185598 hasPrimaryLocation W27831855981 @default.
- W2783185598 hasRelatedWork W1980741455 @default.
- W2783185598 hasRelatedWork W2237671050 @default.
- W2783185598 hasRelatedWork W2524708987 @default.
- W2783185598 hasRelatedWork W2606806821 @default.
- W2783185598 hasRelatedWork W2635471793 @default.
- W2783185598 hasRelatedWork W2777864948 @default.
- W2783185598 hasRelatedWork W2783984851 @default.
- W2783185598 hasRelatedWork W2787650696 @default.
- W2783185598 hasRelatedWork W2797110164 @default.
- W2783185598 hasRelatedWork W2802440401 @default.
- W2783185598 hasRelatedWork W2893399179 @default.
- W2783185598 hasRelatedWork W2899638089 @default.