A
Anocha Rugchatjaroen
Researcher at Thailand National Science and Technology Development Agency
Publications - 21
Citations - 88
Anocha Rugchatjaroen is an academic researcher from Thailand National Science and Technology Development Agency. The author has contributed to research in topics: Convolutional neural network & Radial basis function network. The author has an hindex of 4, co-authored 21 publications receiving 62 citations. Previous affiliations of Anocha Rugchatjaroen include University of York & Chulalongkorn University.
Papers
More filters
Proceedings ArticleDOI
A Light-Weight Artificial Neural Network for Speech Emotion Recognition using Average Values of MFCCs and Their Derivatives
Panuwit Nantasri,Ekachai Phaisangittisagul,Jessada Karnjana,Surasak Boonkla,Suthum Keerativittayanun,Anocha Rugchatjaroen,Sasiporn Usanavasin,Takahiro Shinozaki +7 more
TL;DR: A novel approach to create a useful set of features for improving speech emotion recognition (SER) system by concatenating average values of MFCCs that are concatenated with delta and delta-delta coefficients to reduce the number of parameters and computational burden.
Proceedings ArticleDOI
A learning method for Thai phonetization of English words.
TL;DR: The proposed model is totally data-driven, starting by automatic grapheme-phoneme alignment, modeling transduction rules and predicting Thai syllabictones using learning machines and achieves acceptable results in both objective and text-tospeech synthesis subjective tests.
Proceedings ArticleDOI
T-tilt: a modified tilt model for F0 analysis and synthesis in tonal languages.
Ausdang Thangthai,Nattanun Thatphithakkul,Chai Wutiwiwatchai,Anocha Rugchatjaroen,Sittipong Saychum +4 more
TL;DR: A modified Tilt model for analyzing and synthesizing F0 contours in tonal languages, called T-Tilt, is proposed, which requires extensive work on parameter synthesis although the synthesizing performance is comparable to those produced by other proposed models.
Proceedings ArticleDOI
The First Wikipedia Questions and Factoid Answers Corpus in the Thai Language
TL;DR: A Thai questions-answers corpus for a question-ANSwering task which was extracted from Thai Wikipedia which was downloaded on 17 December 2017 and comprises 5,000 annotated factoids.
Journal ArticleDOI
Efficient two-stage processing for joint sequence model-based Thai grapheme-to-phoneme conversion
Anocha Rugchatjaroen,Sittipong Saychum,Sarawoot Kongyoung,Patcharika Chootrakool,Sawit Kasuriya,Chai Wutiwiwatchai +5 more
TL;DR: A novel two-stage processing for Thai G2P is introduced, with as much as 14.49% absolute improvement from a baseline model using Context Free Grammar syllabification and syllable n-gram modeling.