Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081982909> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W3081982909 abstract "The accuracy of the automatic speech recognition (ASR) system will decrease under reverberant conditions. Feature enhancement as the front-end of an ASR system can improve the performance in adverse environments. In this research work, we propose modified masking based deep learning method to enhance the log Mel filterbank coefficients of reverberant speech. We eliminate the zero-value amplitude output by adding an adjustment layer to the DNN, thus improving the accuracy of spectral feature estimation. As the masking method relies on the human hearing mechanism, its feature enhancement effect is superior than the state-of-the-art spectral feature mapping method. ASR experiments with the REVERB 2014 stereo (reverberant and clean) data proved that the proposed method achieved excellent results." @default.
- W3081982909 created "2020-09-08" @default.
- W3081982909 creator A5017251198 @default.
- W3081982909 creator A5050763764 @default.
- W3081982909 creator A5058725877 @default.
- W3081982909 date "2020-06-01" @default.
- W3081982909 modified "2023-10-16" @default.
- W3081982909 title "Masking based Spectral Feature Enhancement for Robust Automatic Speech Recognition" @default.
- W3081982909 cites W1482149378 @default.
- W3081982909 cites W1591676560 @default.
- W3081982909 cites W1665214252 @default.
- W3081982909 cites W1836465849 @default.
- W3081982909 cites W190004713 @default.
- W3081982909 cites W2042071805 @default.
- W3081982909 cites W2044893557 @default.
- W3081982909 cites W2069681747 @default.
- W3081982909 cites W2078528584 @default.
- W3081982909 cites W2086139506 @default.
- W3081982909 cites W2130722890 @default.
- W3081982909 cites W2141411743 @default.
- W3081982909 cites W2144786298 @default.
- W3081982909 cites W2172097686 @default.
- W3081982909 cites W2242685705 @default.
- W3081982909 cites W2291877678 @default.
- W3081982909 cites W2399557756 @default.
- W3081982909 cites W2609317876 @default.
- W3081982909 cites W2802304149 @default.
- W3081982909 cites W2890820256 @default.
- W3081982909 cites W2962866211 @default.
- W3081982909 doi "https://doi.org/10.1109/icaica50127.2020.9181915" @default.
- W3081982909 hasPublicationYear "2020" @default.
- W3081982909 type Work @default.
- W3081982909 sameAs 3081982909 @default.
- W3081982909 citedByCount "0" @default.
- W3081982909 crossrefType "proceedings-article" @default.
- W3081982909 hasAuthorship W3081982909A5017251198 @default.
- W3081982909 hasAuthorship W3081982909A5050763764 @default.
- W3081982909 hasAuthorship W3081982909A5058725877 @default.
- W3081982909 hasConcept C138885662 @default.
- W3081982909 hasConcept C142362112 @default.
- W3081982909 hasConcept C153180895 @default.
- W3081982909 hasConcept C153349607 @default.
- W3081982909 hasConcept C154945302 @default.
- W3081982909 hasConcept C163294075 @default.
- W3081982909 hasConcept C2776182073 @default.
- W3081982909 hasConcept C2776401178 @default.
- W3081982909 hasConcept C2777402240 @default.
- W3081982909 hasConcept C28490314 @default.
- W3081982909 hasConcept C41008148 @default.
- W3081982909 hasConcept C41895202 @default.
- W3081982909 hasConcept C52622490 @default.
- W3081982909 hasConcept C61328038 @default.
- W3081982909 hasConceptScore W3081982909C138885662 @default.
- W3081982909 hasConceptScore W3081982909C142362112 @default.
- W3081982909 hasConceptScore W3081982909C153180895 @default.
- W3081982909 hasConceptScore W3081982909C153349607 @default.
- W3081982909 hasConceptScore W3081982909C154945302 @default.
- W3081982909 hasConceptScore W3081982909C163294075 @default.
- W3081982909 hasConceptScore W3081982909C2776182073 @default.
- W3081982909 hasConceptScore W3081982909C2776401178 @default.
- W3081982909 hasConceptScore W3081982909C2777402240 @default.
- W3081982909 hasConceptScore W3081982909C28490314 @default.
- W3081982909 hasConceptScore W3081982909C41008148 @default.
- W3081982909 hasConceptScore W3081982909C41895202 @default.
- W3081982909 hasConceptScore W3081982909C52622490 @default.
- W3081982909 hasConceptScore W3081982909C61328038 @default.
- W3081982909 hasLocation W30819829091 @default.
- W3081982909 hasOpenAccess W3081982909 @default.
- W3081982909 hasPrimaryLocation W30819829091 @default.
- W3081982909 hasRelatedWork W10974996 @default.
- W3081982909 hasRelatedWork W11553578 @default.
- W3081982909 hasRelatedWork W12329832 @default.
- W3081982909 hasRelatedWork W14456953 @default.
- W3081982909 hasRelatedWork W445403 @default.
- W3081982909 hasRelatedWork W5319273 @default.
- W3081982909 hasRelatedWork W6882942 @default.
- W3081982909 hasRelatedWork W7296353 @default.
- W3081982909 hasRelatedWork W9143300 @default.
- W3081982909 hasRelatedWork W9692546 @default.
- W3081982909 isParatext "false" @default.
- W3081982909 isRetracted "false" @default.
- W3081982909 magId "3081982909" @default.
- W3081982909 workType "article" @default.