SemOpenAlex |

SemOpenAlex

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2023407680> ?p ?o ?g. }

Showing items 1 to 71 of 71 with 100 items per page.

W2023407680 endingPage "273" @default.
W2023407680 startingPage "260" @default.
W2023407680 abstract "We present an articulatory-to-acoustic mapping for real-time articulatory synthesis.The method uses a deep neural network with a tapped-delay input line.Tapped-delay line efficiently captures dynamics in articulatory trajectories.The model achieved higher accuracy than competing models based on Gaussian mixtures.The improvement was also found perceivable in a subjective listening test. The conventional approach for data-driven articulatory synthesis consists of modeling the joint acoustic-articulatory distribution with a Gaussian mixture model (GMM), followed by a post-processing step that optimizes the resulting acoustic trajectories. This final step can significantly improve the accuracy of the GMM frame-by-frame mapping but is computationally intensive and requires that the entire utterance be synthesized beforehand, making it unsuited for real-time synthesis. To address this issue, we present a deep neural network (DNN) articulatory synthesizer that uses a tapped-delay input line, allowing the model to capture context information in the articulatory trajectory without the need for post-processing. We characterize the DNN as a function of the context size and number of hidden layers, and compare it against two GMM articulatory synthesizers, a baseline model that performs a simple frame-by-frame mapping, and a second model that also performs trajectory optimization. Our results show that a DNN with a 60-ms context window and two 512-neuron hidden layers can synthesize speech at four times the frame rate - comparable to frame-by-frame mappings, while improving the accuracy of trajectory optimization (a 9.8% reduction in Mel Cepstral distortion). Subjective evaluation through pairwise listening tests also shows a strong preference toward the DNN articulatory synthesizer when compared to GMM trajectory optimization." @default.
W2023407680 created "2016-06-24" @default.
W2023407680 creator A5036468647 @default.
W2023407680 creator A5062423099 @default.
W2023407680 date "2016-03-01" @default.
W2023407680 modified "2023-10-18" @default.
W2023407680 title "Data driven articulatory synthesis with deep neural networks" @default.
W2023407680 cites W1498436455 @default.
W2023407680 cites W1977591085 @default.
W2023407680 cites W1982854652 @default.
W2023407680 cites W1990394889 @default.
W2023407680 cites W2008120082 @default.
W2023407680 cites W2017917005 @default.
W2023407680 cites W2023728986 @default.
W2023407680 cites W2033353676 @default.
W2023407680 cites W2034829178 @default.
W2023407680 cites W2078528584 @default.
W2023407680 cites W2079402412 @default.
W2023407680 cites W2120605154 @default.
W2023407680 cites W2160815625 @default.
W2023407680 cites W2406654659 @default.
W2023407680 cites W78272257 @default.
W2023407680 doi "https://doi.org/10.1016/j.csl.2015.02.003" @default.
W2023407680 hasPublicationYear "2016" @default.
W2023407680 type Work @default.
W2023407680 sameAs 2023407680 @default.
W2023407680 citedByCount "29" @default.
W2023407680 countsByYear W20234076802015 @default.
W2023407680 countsByYear W20234076802016 @default.
W2023407680 countsByYear W20234076802017 @default.
W2023407680 countsByYear W20234076802018 @default.
W2023407680 countsByYear W20234076802019 @default.
W2023407680 countsByYear W20234076802020 @default.
W2023407680 countsByYear W20234076802021 @default.
W2023407680 countsByYear W20234076802022 @default.
W2023407680 countsByYear W20234076802023 @default.
W2023407680 crossrefType "journal-article" @default.
W2023407680 hasAuthorship W2023407680A5036468647 @default.
W2023407680 hasAuthorship W2023407680A5062423099 @default.
W2023407680 hasConcept C154945302 @default.
W2023407680 hasConcept C204321447 @default.
W2023407680 hasConcept C28490314 @default.
W2023407680 hasConcept C2984842247 @default.
W2023407680 hasConcept C41008148 @default.
W2023407680 hasConcept C50644808 @default.
W2023407680 hasConceptScore W2023407680C154945302 @default.
W2023407680 hasConceptScore W2023407680C204321447 @default.
W2023407680 hasConceptScore W2023407680C28490314 @default.
W2023407680 hasConceptScore W2023407680C2984842247 @default.
W2023407680 hasConceptScore W2023407680C41008148 @default.
W2023407680 hasConceptScore W2023407680C50644808 @default.
W2023407680 hasLocation W20234076801 @default.
W2023407680 hasOpenAccess W2023407680 @default.
W2023407680 hasPrimaryLocation W20234076801 @default.
W2023407680 hasRelatedWork W1552159754 @default.
W2023407680 hasRelatedWork W2131420137 @default.
W2023407680 hasRelatedWork W2148757832 @default.
W2023407680 hasRelatedWork W2293457016 @default.
W2023407680 hasRelatedWork W2368651715 @default.
W2023407680 hasRelatedWork W2386387936 @default.
W2023407680 hasRelatedWork W2611614995 @default.
W2023407680 hasRelatedWork W2789919619 @default.
W2023407680 hasRelatedWork W3107474891 @default.
W2023407680 hasRelatedWork W4321496520 @default.
W2023407680 hasVolume "36" @default.
W2023407680 isParatext "false" @default.
W2023407680 isRetracted "false" @default.
W2023407680 magId "2023407680" @default.
W2023407680 workType "article" @default.