Matches in SemOpenAlex for { <https://semopenalex.org/work/W2061778110> ?p ?o ?g. }
- W2061778110 abstract "While human listeners can understand speech in reverberant conditions, indicating that the auditory system is robust to such degradations, reverberation leads to high word error rates for automatic speech recognition (ASR) systems. In this work, we present robust acoustic features motivated by human speech perception for use in a convolutional deep neural network (CDNN)-based acoustic model for recognizing continuous speech in a reverberant condition. Using a single-feature system trained with the single channel data distributed through the REVERB 2014 challenge on ASR in reverberant conditions, we show a substantial relative reduction in word error rates (WERs) compared to the conventional filterbank energy-based features for single-channel simulated and real reverberation conditions. The reduction is more pronounced when multiple features and systems were combined together. The proposed system outperforms the best system reported in REVERB-2014 challenge in single channel full-batch processing task." @default.
- W2061778110 created "2016-06-24" @default.
- W2061778110 creator A5065509001 @default.
- W2061778110 creator A5066920453 @default.
- W2061778110 creator A5091201226 @default.
- W2061778110 date "2014-12-01" @default.
- W2061778110 modified "2023-09-25" @default.
- W2061778110 title "Deep convolutional nets and robust features for reverberation-robust speech recognition" @default.
- W2061778110 cites W1498638354 @default.
- W2061778110 cites W1515932869 @default.
- W2061778110 cites W1904457459 @default.
- W2061778110 cites W1981730446 @default.
- W2061778110 cites W1989314204 @default.
- W2061778110 cites W1993882792 @default.
- W2061778110 cites W2024490156 @default.
- W2061778110 cites W2079623482 @default.
- W2061778110 cites W2108072369 @default.
- W2061778110 cites W2110322414 @default.
- W2061778110 cites W2112739286 @default.
- W2061778110 cites W2114537326 @default.
- W2061778110 cites W2125471631 @default.
- W2061778110 cites W2130722890 @default.
- W2061778110 cites W2140979961 @default.
- W2061778110 cites W2147166770 @default.
- W2061778110 cites W2150769028 @default.
- W2061778110 cites W2155273149 @default.
- W2061778110 cites W2158273884 @default.
- W2061778110 cites W2187325407 @default.
- W2061778110 cites W2395321025 @default.
- W2061778110 cites W2398177287 @default.
- W2061778110 cites W2406171445 @default.
- W2061778110 doi "https://doi.org/10.1109/slt.2014.7078633" @default.
- W2061778110 hasPublicationYear "2014" @default.
- W2061778110 type Work @default.
- W2061778110 sameAs 2061778110 @default.
- W2061778110 citedByCount "8" @default.
- W2061778110 countsByYear W20617781102015 @default.
- W2061778110 countsByYear W20617781102016 @default.
- W2061778110 countsByYear W20617781102017 @default.
- W2061778110 countsByYear W20617781102018 @default.
- W2061778110 countsByYear W20617781102020 @default.
- W2061778110 crossrefType "proceedings-article" @default.
- W2061778110 hasAuthorship W2061778110A5065509001 @default.
- W2061778110 hasAuthorship W2061778110A5066920453 @default.
- W2061778110 hasAuthorship W2061778110A5091201226 @default.
- W2061778110 hasConcept C100515483 @default.
- W2061778110 hasConcept C111335779 @default.
- W2061778110 hasConcept C121332964 @default.
- W2061778110 hasConcept C127162648 @default.
- W2061778110 hasConcept C138885662 @default.
- W2061778110 hasConcept C153180895 @default.
- W2061778110 hasConcept C154945302 @default.
- W2061778110 hasConcept C24890656 @default.
- W2061778110 hasConcept C2524010 @default.
- W2061778110 hasConcept C2776401178 @default.
- W2061778110 hasConcept C28490314 @default.
- W2061778110 hasConcept C33923547 @default.
- W2061778110 hasConcept C40969351 @default.
- W2061778110 hasConcept C41008148 @default.
- W2061778110 hasConcept C41895202 @default.
- W2061778110 hasConcept C61328038 @default.
- W2061778110 hasConcept C76155785 @default.
- W2061778110 hasConcept C81363708 @default.
- W2061778110 hasConcept C90805587 @default.
- W2061778110 hasConcept C95851461 @default.
- W2061778110 hasConceptScore W2061778110C100515483 @default.
- W2061778110 hasConceptScore W2061778110C111335779 @default.
- W2061778110 hasConceptScore W2061778110C121332964 @default.
- W2061778110 hasConceptScore W2061778110C127162648 @default.
- W2061778110 hasConceptScore W2061778110C138885662 @default.
- W2061778110 hasConceptScore W2061778110C153180895 @default.
- W2061778110 hasConceptScore W2061778110C154945302 @default.
- W2061778110 hasConceptScore W2061778110C24890656 @default.
- W2061778110 hasConceptScore W2061778110C2524010 @default.
- W2061778110 hasConceptScore W2061778110C2776401178 @default.
- W2061778110 hasConceptScore W2061778110C28490314 @default.
- W2061778110 hasConceptScore W2061778110C33923547 @default.
- W2061778110 hasConceptScore W2061778110C40969351 @default.
- W2061778110 hasConceptScore W2061778110C41008148 @default.
- W2061778110 hasConceptScore W2061778110C41895202 @default.
- W2061778110 hasConceptScore W2061778110C61328038 @default.
- W2061778110 hasConceptScore W2061778110C76155785 @default.
- W2061778110 hasConceptScore W2061778110C81363708 @default.
- W2061778110 hasConceptScore W2061778110C90805587 @default.
- W2061778110 hasConceptScore W2061778110C95851461 @default.
- W2061778110 hasLocation W20617781101 @default.
- W2061778110 hasOpenAccess W2061778110 @default.
- W2061778110 hasPrimaryLocation W20617781101 @default.
- W2061778110 hasRelatedWork W1485840222 @default.
- W2061778110 hasRelatedWork W1550695516 @default.
- W2061778110 hasRelatedWork W1583048384 @default.
- W2061778110 hasRelatedWork W1598508708 @default.
- W2061778110 hasRelatedWork W1964143424 @default.
- W2061778110 hasRelatedWork W2008146117 @default.
- W2061778110 hasRelatedWork W2042071805 @default.
- W2061778110 hasRelatedWork W2075754845 @default.
- W2061778110 hasRelatedWork W2292655135 @default.
- W2061778110 hasRelatedWork W2295541562 @default.
- W2061778110 hasRelatedWork W2406171445 @default.
- W2061778110 hasRelatedWork W2557515336 @default.