Sign in

Estimating Underlying Articulatory Targets of Thai Vowels by Using Deep Learning Based on Generating Synthetic Samples From a 3D Vocal Tract Model and Data Augmentation.

Thanat LapthawanSantitham Prom-onPeter BirkholzYi Xu
Published in: IEEE Access (2022)
Keyphrases
  • data sets
  • deep learning
  • vocal tract
  • data points
  • high dimensional
  • neural network
  • training data
  • probabilistic model
  • speech recognition
  • information retrieval
  • similarity measure
  • bayesian networks
  • text mining