Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

PROSODIC BOUNDARY PREDICTION MODEL FOR VIETNAMESE TEXT-TO-SPEECH

Abstract: 

Prosodic boundary is a crucial prosodic cue of prosodic phrasing. This research aims to build a prosodic boundary prediction model for improving the naturalness of the Viet- namese speech synthesis. This model can be used directly to predict prosodic boundaries in synthesis phase of the statisti- cal parametric speech synthesis (e.g. Hidden Markov Model - HMM, Deep Neural Network - DNN). It can also be used to improve the quality of the training phase in the end-to- end speech synthesis (e.g. Tacotron). Beside a conventional feature of Part-Of-Speech (POS), the authors proposes two novel and efficient features to predict prosodic boundaries: syntactic blocks and syntactic links. Syntactic blocks are syn- tactic phrases whose sizes are bounded. The syntactic link of a word was a syntax tree-based relationship with the pre- vious word. These two important predictors are found based on a thorough analysis on VDTO Vietnamese corpus to find out a correlation between hierarchical syntactic information and pause appearance. The bounded size of syntactic blocks was discovered to be an optimal value of 10 syllables. The proposed features are experimented with the decision tree classification algorithm. The two novel predictors help the proposed model improve about 36.4% to the model with only POS features. The combination of all three predictors give the best F1-score results at 81.2% in 10-fold cross-validation and at 81.4% in test data.

up
0 users have voted:

Paper Details

Authors:
Nguyen Thi Thu Trang, Nguyen Hoang Ky, Albert Rilliard, Christophe D’Alessandro
Submitted On:
22 October 2020 - 8:15am
Short Link:
Type:
Research Manuscript
Event:
Presenter's Name:
Nguyen Thi Thu Trang
Document Year:
2021
Cite

Document Files

ICASSP_2021_Prosodic_Boundary_Prediction.pdf

(16)

ICASSP_2021_Prosodic_Boundary_Prediction.pdf

(13)

ICASSP_2021_Prosodic_Boundary_Prediction.pdf

(10)

Subscribe

[1] Nguyen Thi Thu Trang, Nguyen Hoang Ky, Albert Rilliard, Christophe D’Alessandro, "PROSODIC BOUNDARY PREDICTION MODEL FOR VIETNAMESE TEXT-TO-SPEECH", IEEE SigPort, 2020. [Online]. Available: http://sigport.org/5466. Accessed: Nov. 29, 2020.
@article{5466-20,
url = {http://sigport.org/5466},
author = {Nguyen Thi Thu Trang; Nguyen Hoang Ky; Albert Rilliard; Christophe D’Alessandro },
publisher = {IEEE SigPort},
title = {PROSODIC BOUNDARY PREDICTION MODEL FOR VIETNAMESE TEXT-TO-SPEECH},
year = {2020} }
TY - EJOUR
T1 - PROSODIC BOUNDARY PREDICTION MODEL FOR VIETNAMESE TEXT-TO-SPEECH
AU - Nguyen Thi Thu Trang; Nguyen Hoang Ky; Albert Rilliard; Christophe D’Alessandro
PY - 2020
PB - IEEE SigPort
UR - http://sigport.org/5466
ER -
Nguyen Thi Thu Trang, Nguyen Hoang Ky, Albert Rilliard, Christophe D’Alessandro. (2020). PROSODIC BOUNDARY PREDICTION MODEL FOR VIETNAMESE TEXT-TO-SPEECH. IEEE SigPort. http://sigport.org/5466
Nguyen Thi Thu Trang, Nguyen Hoang Ky, Albert Rilliard, Christophe D’Alessandro, 2020. PROSODIC BOUNDARY PREDICTION MODEL FOR VIETNAMESE TEXT-TO-SPEECH. Available at: http://sigport.org/5466.
Nguyen Thi Thu Trang, Nguyen Hoang Ky, Albert Rilliard, Christophe D’Alessandro. (2020). "PROSODIC BOUNDARY PREDICTION MODEL FOR VIETNAMESE TEXT-TO-SPEECH." Web.
1. Nguyen Thi Thu Trang, Nguyen Hoang Ky, Albert Rilliard, Christophe D’Alessandro. PROSODIC BOUNDARY PREDICTION MODEL FOR VIETNAMESE TEXT-TO-SPEECH [Internet]. IEEE SigPort; 2020. Available from : http://sigport.org/5466