Matches in SemOpenAlex for { <https://semopenalex.org/work/W3140455833> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3140455833 abstract "This paper presents an unsupervised learning method of deep neural networks that perform acoustic-to-articulatory inversion for arbitrary utterances. Conventional unsupervised acoustic-to-articulatory inversion methods are based on the analysis-by-synthesis approach and non-linear optimization algorithms. One limitation is that they require time-consuming iterative optimizations to obtain articulatory parameters for a given target speech segment. Neural networks, after learning their relationship, can obtain these articulatory parameters without an iterative optimization. However, conventional methods need supervised learning and paired acoustic and articulatory samples. We propose a hybrid auto-encoder based unsupervised learning framework for the acoustic-to-articulatory inversion neural networks that can capture context information. The essential point of the framework is making the training effective. We investigate several reinforcement learning algorithms and show the usefulness of the deterministic policy gradient. Experimental results demonstrate that the proposed method can infer articulatory parameters not only for training set segments but also for unseen utterances. Averaged reconstruction errors achieved for open test samples are similar to or even lower than the conventional method that directly optimizes the articulatory parameters in a closed condition." @default.
- W3140455833 created "2021-04-13" @default.
- W3140455833 creator A5003049061 @default.
- W3140455833 creator A5049107389 @default.
- W3140455833 creator A5049320370 @default.
- W3140455833 date "2021-01-19" @default.
- W3140455833 modified "2023-09-27" @default.
- W3140455833 title "Unsupervised Acoustic-to-Articulatory Inversion Neural Network Learning Based on Deterministic Policy Gradient" @default.
- W3140455833 cites W1494198834 @default.
- W3140455833 cites W1531956331 @default.
- W3140455833 cites W1595153059 @default.
- W3140455833 cites W1965378753 @default.
- W3140455833 cites W1969229349 @default.
- W3140455833 cites W1990394889 @default.
- W3140455833 cites W2006775235 @default.
- W3140455833 cites W2027933203 @default.
- W3140455833 cites W2030671974 @default.
- W3140455833 cites W2067295501 @default.
- W3140455833 cites W2105478683 @default.
- W3140455833 cites W2119717200 @default.
- W3140455833 cites W2154920538 @default.
- W3140455833 cites W2191779130 @default.
- W3140455833 cites W2286699414 @default.
- W3140455833 cites W2509129594 @default.
- W3140455833 cites W2888898948 @default.
- W3140455833 doi "https://doi.org/10.1109/slt48900.2021.9383554" @default.
- W3140455833 hasPublicationYear "2021" @default.
- W3140455833 type Work @default.
- W3140455833 sameAs 3140455833 @default.
- W3140455833 citedByCount "1" @default.
- W3140455833 countsByYear W31404558332022 @default.
- W3140455833 crossrefType "proceedings-article" @default.
- W3140455833 hasAuthorship W3140455833A5003049061 @default.
- W3140455833 hasAuthorship W3140455833A5049107389 @default.
- W3140455833 hasAuthorship W3140455833A5049320370 @default.
- W3140455833 hasConcept C109007969 @default.
- W3140455833 hasConcept C151730666 @default.
- W3140455833 hasConcept C153180895 @default.
- W3140455833 hasConcept C154945302 @default.
- W3140455833 hasConcept C1893757 @default.
- W3140455833 hasConcept C28490314 @default.
- W3140455833 hasConcept C41008148 @default.
- W3140455833 hasConcept C50644808 @default.
- W3140455833 hasConcept C8038995 @default.
- W3140455833 hasConcept C86803240 @default.
- W3140455833 hasConceptScore W3140455833C109007969 @default.
- W3140455833 hasConceptScore W3140455833C151730666 @default.
- W3140455833 hasConceptScore W3140455833C153180895 @default.
- W3140455833 hasConceptScore W3140455833C154945302 @default.
- W3140455833 hasConceptScore W3140455833C1893757 @default.
- W3140455833 hasConceptScore W3140455833C28490314 @default.
- W3140455833 hasConceptScore W3140455833C41008148 @default.
- W3140455833 hasConceptScore W3140455833C50644808 @default.
- W3140455833 hasConceptScore W3140455833C8038995 @default.
- W3140455833 hasConceptScore W3140455833C86803240 @default.
- W3140455833 hasLocation W31404558331 @default.
- W3140455833 hasOpenAccess W3140455833 @default.
- W3140455833 hasPrimaryLocation W31404558331 @default.
- W3140455833 hasRelatedWork W1548481688 @default.
- W3140455833 hasRelatedWork W2026253357 @default.
- W3140455833 hasRelatedWork W2095752956 @default.
- W3140455833 hasRelatedWork W2592385986 @default.
- W3140455833 hasRelatedWork W2695951553 @default.
- W3140455833 hasRelatedWork W2775464024 @default.
- W3140455833 hasRelatedWork W2776466379 @default.
- W3140455833 hasRelatedWork W2899683012 @default.
- W3140455833 hasRelatedWork W3090869887 @default.
- W3140455833 hasRelatedWork W3108696707 @default.
- W3140455833 isParatext "false" @default.
- W3140455833 isRetracted "false" @default.
- W3140455833 magId "3140455833" @default.
- W3140455833 workType "article" @default.