Chinese prosodic word prediction using the conditional random fields

Authors:
Honghui Dong;Yong Qin;Limin Jia
Affiliations:
State Key Laboratory of Rail Traffic Control and Safety, Traffic and Transportation School, Beijing Jiaotong University, Beijing, China;State Key Laboratory of Rail Traffic Control and Safety, Traffic and Transportation School, Beijing Jiaotong University, Beijing, China;State Key Laboratory of Rail Traffic Control and Safety, Traffic and Transportation School, Beijing Jiaotong University, Beijing, China
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 1
Year:
2009

Citing 4
Cited 0

A maximum entropy approach to natural language processing

Computational Linguistics
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data

ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Segmenting unrestricted Chinese text into prosodic words instead of lexical words

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 200. on IEEE International Conference - Volume 02
Prosodic word prediction using a maximum entropy approach

ISCSLP'06 Proceedings of the 5th international conference on Chinese Spoken Language Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

As the basic prosodic unit, the prosodic word play an important role for the naturalness and the intelligibility for the Chinese TTS system. Although many research work have been on this research direction, the precision of the prosodic word prediction is still not satisfying. In this paper, Conditional Random Fields is introduced to model the prosodic predicting process. In this model, more efficient features can be fused together. Compared with the ME model, the CRF model can describe the interacting relations between the neighboring prosodic words. The experiment results show that this Conditional Random Fields Model is competent for the prosodic word prediction task. The f-score of the prosodic word boundary prediction reaches 96.81%.