A Tool to Solve Sentence Segmentation Problem on Preparing Speech Database for Indonesian Text-to-speech System

被引：5

作者：

Uliniansyah, Mohammad Teduh ^{[1
]}

Gunarso ^{[1
]}

Nurfadhilah, Elvira ^{[1
]}

Aini, Lyla Ruslana ^{[1
]}

Junde, Juliati ^{[1
]}

Ayuningtyas, Fara ^{[1
]}

Santosa, Agung ^{[1
]}

机构：

[1] BPPT, Ctr Informat & Commun Technol, Puspiptek Serpong 15314, Tangerang Selat, Indonesia

来源：

SLTU-2016 5TH WORKSHOP ON SPOKEN LANGUAGE TECHNOLOGIES FOR UNDER-RESOURCED LANGUAGES | 2016年 / 81卷

关键词：

training data; TTS; segmenting audio data; Bahasa Indonesia; Syllable-timed;

D O I：

10.1016/j.procs.2016.04.048

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Creating a training data ready to be used for developing a text-to-speech (TTS) system can be a difficult task, since sometimes the recorded audio data is not the same with the prepared texts. To overcome differences between audio and text data, we developed a tool to segment audio data into sentences. As it is known, doing sentence segmentation of audio data manually needs efforts and resources. This paper presents a solution for alleviating problems encountered during segmentation process of audio data for developing an Indonesian TTS system. The tool was developed based on a fact that bahasa Indonesia is a syllable-timed language. We found that our tool reduces resources needed for segmenting Indonesian audio data. (C) 2016 Published by Elsevier B.V.

引用

页码：188 / 193

页数：6

共 6 条

[1]

Alwi Hasan., 2003, Tata Bahasa Baku Bahasa Indonesia

[2] STRESS-TIMING AND SYLLABLE-TIMING REANALYZED [J].

DAUER, RM .

JOURNAL OF PHONETICS, 1983, 11 (01) :51-62

[3]

Dekens Tomas, 2014, SIGN PROC C EUSIPCO, P1252

[4]

Gotoh Y., 2000, SENTENCE BOUNDARY DE

[5]

Liu Y., 2005, P ANN M ASS COMPUTAT, P451, DOI DOI 10.3115/1219840.1219896

[6] Prosody-based automatic segmentation of speech into sentences and topics [J].

Shriberg, E ;

Stolcke, A ;

Hakkani-Tür, D ;

Tür, G .

SPEECH COMMUNICATION, 2000, 32 (1-2) :127-154

← 1 →