Matches in SemOpenAlex for { <https://semopenalex.org/work/W2587942996> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W2587942996 endingPage "516" @default.
- W2587942996 startingPage "496" @default.
- W2587942996 abstract "Abstract Because speech recorded by distant microphones in real-world environments is contaminated by both additive noise and reverberation, the automatic speech recognition (ASR) performance is seriously degraded due to the mismatch between the training and testing environments. In the previous studies, some of the authors proposed a Bayesian feature enhancement (BFE) method with re-estimation of reverberation filter parameters for reverberant speech recognition and a BFE method employing independent vector analysis (IVA) to deal with speech corrupted by additive noise. Although both of them accomplish significant improvements in either reverberation- or noise-robust ASR, most of the real-world environments involve both additive noise and reverberation. For robust ASR in the noisy reverberant environments, in this paper, we present a hidden-Markov-model (HMM)-based BFE method using IVA and reverberation parameter re-estimation (RPR) to remove additive and reverberant distortion components in speech acquired by multi-microphones effectively by introducing Bayesian inference in the observation model of input speech features. Experimental results show that the presented method can further reduce the word error rates (WERs) compared with the BFE methods based on conventional noise and/or reverberation models and combinations of the BFE methods for reverberation- or noise-robust ASR." @default.
- W2587942996 created "2017-02-24" @default.
- W2587942996 creator A5002418613 @default.
- W2587942996 creator A5051359358 @default.
- W2587942996 creator A5081018770 @default.
- W2587942996 creator A5089379564 @default.
- W2587942996 date "2017-11-01" @default.
- W2587942996 modified "2023-09-24" @default.
- W2587942996 title "Bayesian feature enhancement using independent vector analysis and reverberation parameter re-estimation for noisy reverberant speech recognition" @default.
- W2587942996 cites W1664684929 @default.
- W2587942996 cites W1979800130 @default.
- W2587942996 cites W1986301630 @default.
- W2587942996 cites W2006547268 @default.
- W2587942996 cites W2009934439 @default.
- W2587942996 cites W2014768838 @default.
- W2587942996 cites W2015143272 @default.
- W2587942996 cites W2016254085 @default.
- W2587942996 cites W2034175551 @default.
- W2587942996 cites W2041509879 @default.
- W2587942996 cites W2061014750 @default.
- W2587942996 cites W2070707809 @default.
- W2587942996 cites W2100818340 @default.
- W2587942996 cites W2107992675 @default.
- W2587942996 cites W2109349638 @default.
- W2587942996 cites W2147706354 @default.
- W2587942996 cites W2159485234 @default.
- W2587942996 cites W2170768669 @default.
- W2587942996 cites W2170912900 @default.
- W2587942996 cites W2466975593 @default.
- W2587942996 cites W280592816 @default.
- W2587942996 doi "https://doi.org/10.1016/j.csl.2017.01.010" @default.
- W2587942996 hasPublicationYear "2017" @default.
- W2587942996 type Work @default.
- W2587942996 sameAs 2587942996 @default.
- W2587942996 citedByCount "2" @default.
- W2587942996 countsByYear W25879429962020 @default.
- W2587942996 countsByYear W25879429962023 @default.
- W2587942996 crossrefType "journal-article" @default.
- W2587942996 hasAuthorship W2587942996A5002418613 @default.
- W2587942996 hasAuthorship W2587942996A5051359358 @default.
- W2587942996 hasAuthorship W2587942996A5081018770 @default.
- W2587942996 hasAuthorship W2587942996A5089379564 @default.
- W2587942996 hasConcept C107673813 @default.
- W2587942996 hasConcept C121332964 @default.
- W2587942996 hasConcept C138885662 @default.
- W2587942996 hasConcept C153180895 @default.
- W2587942996 hasConcept C154945302 @default.
- W2587942996 hasConcept C24890656 @default.
- W2587942996 hasConcept C2776401178 @default.
- W2587942996 hasConcept C28490314 @default.
- W2587942996 hasConcept C41008148 @default.
- W2587942996 hasConcept C41895202 @default.
- W2587942996 hasConcept C83665646 @default.
- W2587942996 hasConcept C95851461 @default.
- W2587942996 hasConceptScore W2587942996C107673813 @default.
- W2587942996 hasConceptScore W2587942996C121332964 @default.
- W2587942996 hasConceptScore W2587942996C138885662 @default.
- W2587942996 hasConceptScore W2587942996C153180895 @default.
- W2587942996 hasConceptScore W2587942996C154945302 @default.
- W2587942996 hasConceptScore W2587942996C24890656 @default.
- W2587942996 hasConceptScore W2587942996C2776401178 @default.
- W2587942996 hasConceptScore W2587942996C28490314 @default.
- W2587942996 hasConceptScore W2587942996C41008148 @default.
- W2587942996 hasConceptScore W2587942996C41895202 @default.
- W2587942996 hasConceptScore W2587942996C83665646 @default.
- W2587942996 hasConceptScore W2587942996C95851461 @default.
- W2587942996 hasFunder F4320322347 @default.
- W2587942996 hasLocation W25879429961 @default.
- W2587942996 hasOpenAccess W2587942996 @default.
- W2587942996 hasPrimaryLocation W25879429961 @default.
- W2587942996 hasRelatedWork W2015538044 @default.
- W2587942996 hasRelatedWork W2052253960 @default.
- W2587942996 hasRelatedWork W2097297745 @default.
- W2587942996 hasRelatedWork W2125471631 @default.
- W2587942996 hasRelatedWork W2147802381 @default.
- W2587942996 hasRelatedWork W2509918103 @default.
- W2587942996 hasRelatedWork W2785535669 @default.
- W2587942996 hasRelatedWork W2900915105 @default.
- W2587942996 hasRelatedWork W3197541072 @default.
- W2587942996 hasRelatedWork W2480412556 @default.
- W2587942996 hasVolume "46" @default.
- W2587942996 isParatext "false" @default.
- W2587942996 isRetracted "false" @default.
- W2587942996 magId "2587942996" @default.
- W2587942996 workType "article" @default.