J
J. van Santen
Researcher at Oregon Health & Science University
Publications - 8
Citations - 250
J. van Santen is an academic researcher from Oregon Health & Science University. The author has contributed to research in topics: Speech synthesis & Formant. The author has an hindex of 7, co-authored 8 publications receiving 211 citations.
Papers
More filters
Journal ArticleDOI
Subtyping cognitive profiles in Autism Spectrum Disorder using a Functional Random Forest algorithm.
Eric Feczko,N M Balba,Oscar Miranda-Dominguez,Michaela Cordova,Sarah L. Karalunas,Lourdes Irwin,Damion V. Demeter,Alison Presmanes Hill,Beth Hoover Langhorst,J Grieser Painter,J. van Santen,Eric Fombonne,Joel T. Nigg,Damien A. Fair +13 more
TL;DR: This study attempts to identify and characterize cognitive subtypes within the ASD population using the Functional Random Forest (FRF) machine learning classification model, and revealed 3 ASD and 4 TD putative subgroups with unique behavioral profiles.
Proceedings ArticleDOI
Intelligibility of modifications to dysarthric speech
John-Paul Hosom,Alexander Kain,Taniya Mishra,J. van Santen,Melanie Fried-Oken,Janice Staehely +5 more
TL;DR: Dysarthric speech can, in the best case, be modified only at the short-term spectral level to improve intelligibility from 68% to 87%.
Journal ArticleDOI
Formant tracking using context-dependent phonemic information
TL;DR: It is shown that if text or phoneme transcription of speech utterances is available, the error rate can be significantly reduced and the proposed formant-tracking algorithm does not require highly accurate alignment/segmentation.
Journal ArticleDOI
The Contribution of Various Sources of Spectral Mismatch to Audible Discontinuities in a Diphone Database
TL;DR: This paper investigates mid-vowel joins for three vowels with a range of post-vocalic consonant contexts typical for diphone databases and shows mismatch in formant frequencies provides the largest contribution to audible discontinuity, followed by mismatch in overall energy.
Proceedings ArticleDOI
Prosodic factors for predicting local pitch shape
TL;DR: This research presents a factorization scheme based on the foot structure of utterances and shows that this efficient scheme results in a fairly small number of additional diphones that need to be recorded, thereby improving the segmental quality of the synthetic voice.