Machine learning techniques have long been applied in many fields and have gained a lot of success. The purpose of learning processes is generally to obtain a set of parameters based on a given data set by minimizing a certain objective function which can explain the data set in a maximum likelihood or minimum estimation error sense. However, most of the learned parameters are highly data dependent and rarely reflect the true physical mechanism that is involved in the observation data. In order to obtain the inherent knowledge involved in the observed data, it is necessary to combine physical models with learning process rather than only fitting the observations with a black box model. To reveal underlying properties of human speech production, we proposed a learning process based on a physiological articulatory model and a coarticulation model, where both of the models are derived from human mechanisms. A two-layer learning framework was designed to learn the parameters concerned with physiological level using the physiological articulatory model and the parameters in the motor planning level using the coarticulation model. The learning process was carried out on an articulatory database of human speech production. The learned parameters were evaluated by numerical experiments and listening tests. The phonetic targets obtained in the planning stage provided an evidence for understanding the virtual targets of human speech production. As a result, the model based learning process reveals the inherent mechanism of the human speech via the learned parameters with certain physical meaning.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Jianguo WEI, Xugang LU, Jianwu DANG, "A Model-Based Learning Process for Modeling Coarticulation of Human Speech" in IEICE TRANSACTIONS on Information,
vol. E90-D, no. 10, pp. 1582-1591, October 2007, doi: 10.1093/ietisy/e90-d.10.1582.
Abstract: Machine learning techniques have long been applied in many fields and have gained a lot of success. The purpose of learning processes is generally to obtain a set of parameters based on a given data set by minimizing a certain objective function which can explain the data set in a maximum likelihood or minimum estimation error sense. However, most of the learned parameters are highly data dependent and rarely reflect the true physical mechanism that is involved in the observation data. In order to obtain the inherent knowledge involved in the observed data, it is necessary to combine physical models with learning process rather than only fitting the observations with a black box model. To reveal underlying properties of human speech production, we proposed a learning process based on a physiological articulatory model and a coarticulation model, where both of the models are derived from human mechanisms. A two-layer learning framework was designed to learn the parameters concerned with physiological level using the physiological articulatory model and the parameters in the motor planning level using the coarticulation model. The learning process was carried out on an articulatory database of human speech production. The learned parameters were evaluated by numerical experiments and listening tests. The phonetic targets obtained in the planning stage provided an evidence for understanding the virtual targets of human speech production. As a result, the model based learning process reveals the inherent mechanism of the human speech via the learned parameters with certain physical meaning.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e90-d.10.1582/_p
Copy
@ARTICLE{e90-d_10_1582,
author={Jianguo WEI, Xugang LU, Jianwu DANG, },
journal={IEICE TRANSACTIONS on Information},
title={A Model-Based Learning Process for Modeling Coarticulation of Human Speech},
year={2007},
volume={E90-D},
number={10},
pages={1582-1591},
abstract={Machine learning techniques have long been applied in many fields and have gained a lot of success. The purpose of learning processes is generally to obtain a set of parameters based on a given data set by minimizing a certain objective function which can explain the data set in a maximum likelihood or minimum estimation error sense. However, most of the learned parameters are highly data dependent and rarely reflect the true physical mechanism that is involved in the observation data. In order to obtain the inherent knowledge involved in the observed data, it is necessary to combine physical models with learning process rather than only fitting the observations with a black box model. To reveal underlying properties of human speech production, we proposed a learning process based on a physiological articulatory model and a coarticulation model, where both of the models are derived from human mechanisms. A two-layer learning framework was designed to learn the parameters concerned with physiological level using the physiological articulatory model and the parameters in the motor planning level using the coarticulation model. The learning process was carried out on an articulatory database of human speech production. The learned parameters were evaluated by numerical experiments and listening tests. The phonetic targets obtained in the planning stage provided an evidence for understanding the virtual targets of human speech production. As a result, the model based learning process reveals the inherent mechanism of the human speech via the learned parameters with certain physical meaning.},
keywords={},
doi={10.1093/ietisy/e90-d.10.1582},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - A Model-Based Learning Process for Modeling Coarticulation of Human Speech
T2 - IEICE TRANSACTIONS on Information
SP - 1582
EP - 1591
AU - Jianguo WEI
AU - Xugang LU
AU - Jianwu DANG
PY - 2007
DO - 10.1093/ietisy/e90-d.10.1582
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E90-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2007
AB - Machine learning techniques have long been applied in many fields and have gained a lot of success. The purpose of learning processes is generally to obtain a set of parameters based on a given data set by minimizing a certain objective function which can explain the data set in a maximum likelihood or minimum estimation error sense. However, most of the learned parameters are highly data dependent and rarely reflect the true physical mechanism that is involved in the observation data. In order to obtain the inherent knowledge involved in the observed data, it is necessary to combine physical models with learning process rather than only fitting the observations with a black box model. To reveal underlying properties of human speech production, we proposed a learning process based on a physiological articulatory model and a coarticulation model, where both of the models are derived from human mechanisms. A two-layer learning framework was designed to learn the parameters concerned with physiological level using the physiological articulatory model and the parameters in the motor planning level using the coarticulation model. The learning process was carried out on an articulatory database of human speech production. The learned parameters were evaluated by numerical experiments and listening tests. The phonetic targets obtained in the planning stage provided an evidence for understanding the virtual targets of human speech production. As a result, the model based learning process reveals the inherent mechanism of the human speech via the learned parameters with certain physical meaning.
ER -