Show simple item record

dc.contributor.authorSabzi Shahrebabaki, Abdolreza
dc.contributor.authorOlfati, Negar
dc.contributor.authorImran, Ali Shariq
dc.contributor.authorJohnsen, Magne Hallstein
dc.contributor.authorSiniscalchi, Sabato Marco
dc.contributor.authorSvendsen, Torbjørn Karl
dc.date.accessioned2023-10-02T11:57:30Z
dc.date.available2023-10-02T11:57:30Z
dc.date.issued2021-05-13
dc.description.abstractThis paper proposes a two-stage deep feed-forward neural network (DNN) to tackle the acoustic-to-articulatory inversion (AAI) problem. DNNs are a viable solution for the AAI task, but the temporal continuity of the estimated articulatory values has not been exploited properly when a DNN is employed. In this work, we propose to address the lack of any temporal constraints while enforcing a parameter-parsimonious solution by deploying a two-stage solution based only on DNNs: (i) Articulatory trajectories are estimated in a first stage using DNN, and (ii) a temporal window of the estimated trajectories is used in a follow-up DNN stage as a refinement. The first stage estimation could be thought of as an auxiliary additional information that poses some constraints on the inversion process. Experimental evidence demonstrates an average error reduction of 7.51% in terms of RMSE compared to the baseline, and an improvement of 2.39% with respect to Pearson correlation is also attained. Finally, we should point out that AAI is still a highly challenging problem, mainly due to the non-linearity of the acoustic-to-articulatory and one-to-many mapping. It is thus promising that a significant improvement was attained with our simple yet elegant solution.en_US
dc.identifier.citationSabzi Shahrebabaki, Olfati, Imran, Johnsen, Siniscalchi, Svendsen: A Two-Stage Deep Modeling Approach to Articulatory Inversion. In: Androutsos, Plataniotis K, Zhang X. ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2021. IEEEen_US
dc.identifier.cristinIDFRIDAID 2009124
dc.identifier.doi10.1109/ICASSP39728.2021.9413742
dc.identifier.isbn978-1-7281-7606-2
dc.identifier.issn1520-6149
dc.identifier.issn2379-190X
dc.identifier.urihttps://hdl.handle.net/10037/31359
dc.language.isoengen_US
dc.publisherIEEEen_US
dc.rights.accessRightsopenAccessen_US
dc.rights.holderCopyright 2021 The Author(s)en_US
dc.titleA Two-Stage Deep Modeling Approach to Articulatory Inversionen_US
dc.type.versionacceptedVersionen_US
dc.typeChapteren_US
dc.typeBokkapittelen_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record