An RNN-based algorithm to detect prosodic phrase for Chinese TTS

被引：0

作者：

Ying, ZW ^{[1
]}

Shi, XH ^{[1
]}

机构：

[1] Intel China Res Ctr, Beijing Kerry Ctr 0601, Beijing 100020, Peoples R China

来源：

2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING - VOL IV: SIGNAL PROCESSING FOR COMMUNICATIONS; VOL V: SIGNAL PROCESSING EDUCATION SENSOR ARRAY & MULTICHANNEL SIGNAL PROCESSING AUDIO & ELECTROACOUSTICS; VOL VI: SIGNAL PROCESSING THEORY & METHODS STUDENT FORUM | 2001年

关键词：

Chinese Text-to-speech; prosodic phrase; part-of-speech;

D O I：

暂无

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

The goal of the work presented here is to automatically predict the prosodic phrase boundaries from the text for Chinese TTS (text-to-speech) by using the trigram of the POS (part-of-speech) with the info of the breaks between the prior two word-pairs by using a RNN (recurrent neural network). Prosodic phrase boundaries are very important to a Chinese TTS system because it will influence the prosodic model for speech synthesis. In this paper, the algorithm tried to use RNN to find some mapping relationship between the POS sequence and prosodic phrase boundaries, and hoped to improve the naturalness of synthesized speech.

引用

页码：809 / 812

页数：4

共 50 条

[1] Study on prediction of prosodic phrase boundaries in Chinese TTS
Zhao, Ziping
Zhu, Yaoting
SNPD 2007: EIGHTH ACIS INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING, ARTIFICIAL INTELLIGENCE, NETWORKING, AND PARALLEL/DISTRIBUTED COMPUTING, VOL 3, PROCEEDINGS, 2007, : 354 - +
[2] A maximum entropy Markov model for prediction of prosodic phrase boundaries in Chinese TTS
Zhao, Ziping
Zhao, Tingjian
Zhu, Yaoting
GRC: 2007 IEEE INTERNATIONAL CONFERENCE ON GRANULAR COMPUTING, PROCEEDINGS, 2007, : 498 - 501
[3] An RNN-based prosodic information synthesizer for Mandarin text-to-speech
Chen, SH
Hwang, SH
Wang, YR
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1998, 6 (03): : 226 - 239
[4] Rule learning based Chinese prosodic phrase prediction
Tao, JH
Dong, HH
Zhao, S
2003 INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE PROCESSING AND KNOWLEDGE ENGINEERING, PROCEEDINGS, 2003, : 425 - 432
[5] Bidirectional RNN-based private car trajectory reconstruction algorithm
Xiao Z.
Qian X.
Jiang H.
Cai C.
Zeng F.
Tongxin Xuebao/Journal on Communications, 2020, 41 (12): : 171 - 181
[6] Semi Supervised Learning for Prediction of Prosodic Phrase Boundaries in Chinese TTS Using Conditional Random Fields
Zhao, Ziping
Ma, Xirong
Pei, Weidong
ADVANCES IN NEURAL NETWORKS - ISNN 2011, PT II, 2011, 6676 : 477 - 485
[7] RNN-based prosodic modeling for mandarin speech and its application to speech-to-text conversion
Wang, WJ
Liao, YF
Chen, SH
SPEECH COMMUNICATION, 2002, 36 (3-4) : 247 - 265
[8] An RNN-Based Algorithm for Decentralized-Partial-Consensus Constrained Optimization
Xia, Zicong
Liu, Yang
Qiu, Jianlong
Ruan, Qihua
Cao, Jinde
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2023, 34 (01) : 534 - 542
[9] Normalized Vowel Duration Enhanced RNN Prosodic Phrase Detection Model
Wu, Yizhi
Li, Hongyan
Li, Sha
2019 INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING SYSTEMS (SPSS 2019), 2019, : 154 - 158
[10] An RNN-Based IMM Filter Surrogate
Becker, Stefan
Hug, Ronny
Huebner, Wolfgang
Arens, Michael
IMAGE ANALYSIS, 2019, 11482 : 387 - 398

← 1 2 3 4 5 →