• Publications
  • Influence
Modeling tone and intonation in Mandarin and English as a process of target approximation.
  • S. Prom-on, Yi Xu, B. Thipakorn
  • Computer Science, Medicine
  • The Journal of the Acoustical Society of America
  • 21 January 2009
TLDR
This paper reports the development of a quantitative target approximation (qTA) model for generating F(0) contours of speech. Expand
  • 173
  • 25
  • PDF
Morpheme-like prosodic functions: Evidence from acoustic analysis and computational modeling
TLDR
We explore the idea that prosodic functions, such as focus and sentence modality, are analogous to lexical morphemes, the smallest sound units that carry meaning. Expand
  • 30
  • 12
  • PDF
Toward invariant functional representations of variable surface fundamental frequency contours: Synthesizing speech melody via model-based stochastic learning
  • Yi Xu, S. Prom-on
  • Computer Science, Mathematics
  • Speech Commun.
  • 1 February 2014
TLDR
We report the development of PENTAtrainer-A trainable yet deterministic prosody synthesizer based on an articulatory-functional view of speech. Expand
  • 62
  • 8
  • PDF
Quantitative Target Approximation Model: Simulating Underlying Mechanisms of Tones and Intonations
  • S. Prom-on, Yi Xu, B. Thipakorn
  • Computer Science
  • IEEE International Conference on Acoustics Speech…
  • 14 May 2006
TLDR
This paper proposes a quantitative target approximation (qTA) model for simulating tone and intonation. Expand
  • 21
  • 3
Functional Modeling of Tone, Focus and Sentence Type in Mandarin Chinese
TLDR
This paper presents the results of a study on the modeling of the interactions between tone, focus, and sentence type in Mandarin Chinese that have not been systematically modeled before, namely, the neutral tone and question intonation. Expand
  • 15
  • 2
  • PDF
PENTATrainer2: A hypothesis-driven prosody modeling tool
TLDR
PENTATrainer2 can facilitate prosody studies in testing hypotheses and theories against speech data by using an automatic analysis-by-synthesis and stochastic learning algorithm. Expand
  • 15
  • 2
  • PDF
A hybrid approach for Thai word segmentation with crowdsourcing feedback system
TLDR
This paper proposes a new hybrid method for Thai word segmentation using crowd-sourced dictionary integrated with word bi-gram model. Expand
  • 4
  • 2
Thai person name recognition (PNR) using likelihood probability of tokenized words
TLDR
In this paper, we presented a research work in the field of NER with the emphasis on person name recognition (PNR) in Thai text. Expand
  • 3
  • 1
Explaining the PENTA model: a reply to Arvaniti and Ladd
TLDR
This paper presents an overview of the Parallel Encoding and Target Approximation (PENTA) model of speech prosody, in response to an extensive critique by Arvaniti & Ladd (2009). Expand
  • 20
  • 1
Articulatory-functional modeling of speech prosody: a review
TLDR
We show that, at least theoretically, it is beneficial to represent both articulatory mechanisms and communicative functions even if the goal is to just simulate surface prosody. Expand
  • 9
  • 1
  • PDF