Matches in SemOpenAlex for { <https://semopenalex.org/work/W2291687365> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2291687365 abstract "Recognizing speech under noisy condition is an ill-posed problem. The CHiME 3 challenge targets robust speech recognition in realistic environments such as street, bus, caffee and pedestrian areas. We study variants of beamformers used for pre-processing multi-channel speech recordings. In particular, we investigate three variants of generalized side-lobe canceller (GSC) beamformers, i.e. GSC with sparse blocking matrix (BM), GSC with adaptive BM (ABM), and GSC with minimum variance distortionless response (MVDR) and ABM. Furthermore, we apply several post-filters to further enhance the speech signal. We introduce MaxPower postfilters and deep neural postfilters (DPFs). DPFs outperformed our baseline systems significantly when measuring the overall perceptual score (OPS) and the perceptual evaluation of speech quality (PESQ). In particular DPFs achieved an average relative improvement of 17.54% OPS points and 18.28% in PESQ, when compared to the CHiME 3 baseline. DPFs also achieved the best WER when combined with an ASR engine on simulated development and evaluation data, i.e. 8.98% and 10.82% WER. The proposed MaxPower beamformer achieved the best overall WER on CHiME 3 real development and evaluation data, i.e. 14.23% and 22.12%, respectively." @default.
- W2291687365 created "2016-06-24" @default.
- W2291687365 creator A5015798259 @default.
- W2291687365 creator A5028921456 @default.
- W2291687365 creator A5032296366 @default.
- W2291687365 creator A5052535834 @default.
- W2291687365 creator A5077678869 @default.
- W2291687365 date "2015-12-01" @default.
- W2291687365 modified "2023-09-24" @default.
- W2291687365 title "Multi-channel speech processing architectures for noise robust speech recognition: 3rd CHiME challenge results" @default.
- W2291687365 cites W1570838609 @default.
- W2291687365 cites W1621501894 @default.
- W2291687365 cites W1635564296 @default.
- W2291687365 cites W179875071 @default.
- W2291687365 cites W1988851394 @default.
- W2291687365 cites W2005679767 @default.
- W2291687365 cites W2069681747 @default.
- W2291687365 cites W2099984896 @default.
- W2291687365 cites W2105921478 @default.
- W2291687365 cites W2113349214 @default.
- W2291687365 cites W2114719288 @default.
- W2291687365 cites W2120608389 @default.
- W2291687365 cites W2121973264 @default.
- W2291687365 cites W2128687862 @default.
- W2291687365 cites W2154642048 @default.
- W2291687365 cites W2156676906 @default.
- W2291687365 cites W2158143227 @default.
- W2291687365 cites W2289394825 @default.
- W2291687365 cites W4210849719 @default.
- W2291687365 cites W4214498238 @default.
- W2291687365 doi "https://doi.org/10.1109/asru.2015.7404830" @default.
- W2291687365 hasPublicationYear "2015" @default.
- W2291687365 type Work @default.
- W2291687365 sameAs 2291687365 @default.
- W2291687365 citedByCount "4" @default.
- W2291687365 countsByYear W22916873652015 @default.
- W2291687365 countsByYear W22916873652017 @default.
- W2291687365 countsByYear W22916873652023 @default.
- W2291687365 crossrefType "proceedings-article" @default.
- W2291687365 hasAuthorship W2291687365A5015798259 @default.
- W2291687365 hasAuthorship W2291687365A5028921456 @default.
- W2291687365 hasAuthorship W2291687365A5032296366 @default.
- W2291687365 hasAuthorship W2291687365A5052535834 @default.
- W2291687365 hasAuthorship W2291687365A5077678869 @default.
- W2291687365 hasBestOaLocation W22916873652 @default.
- W2291687365 hasConcept C115961682 @default.
- W2291687365 hasConcept C127162648 @default.
- W2291687365 hasConcept C154945302 @default.
- W2291687365 hasConcept C28490314 @default.
- W2291687365 hasConcept C41008148 @default.
- W2291687365 hasConcept C61328038 @default.
- W2291687365 hasConcept C76155785 @default.
- W2291687365 hasConcept C99498987 @default.
- W2291687365 hasConceptScore W2291687365C115961682 @default.
- W2291687365 hasConceptScore W2291687365C127162648 @default.
- W2291687365 hasConceptScore W2291687365C154945302 @default.
- W2291687365 hasConceptScore W2291687365C28490314 @default.
- W2291687365 hasConceptScore W2291687365C41008148 @default.
- W2291687365 hasConceptScore W2291687365C61328038 @default.
- W2291687365 hasConceptScore W2291687365C76155785 @default.
- W2291687365 hasConceptScore W2291687365C99498987 @default.
- W2291687365 hasLocation W22916873651 @default.
- W2291687365 hasLocation W22916873652 @default.
- W2291687365 hasOpenAccess W2291687365 @default.
- W2291687365 hasPrimaryLocation W22916873651 @default.
- W2291687365 hasRelatedWork W1494547797 @default.
- W2291687365 hasRelatedWork W2068198776 @default.
- W2291687365 hasRelatedWork W2069517613 @default.
- W2291687365 hasRelatedWork W2078083007 @default.
- W2291687365 hasRelatedWork W2103878314 @default.
- W2291687365 hasRelatedWork W2367866479 @default.
- W2291687365 hasRelatedWork W2368779261 @default.
- W2291687365 hasRelatedWork W2374918184 @default.
- W2291687365 hasRelatedWork W2418631473 @default.
- W2291687365 hasRelatedWork W4211118001 @default.
- W2291687365 isParatext "false" @default.
- W2291687365 isRetracted "false" @default.
- W2291687365 magId "2291687365" @default.
- W2291687365 workType "article" @default.