Speech Signal Feature Extraction Method of Tibetan Speech Synthesis System Based on Machine Learning

被引：0
|
作者：
Liu, Ze-guo [1 ]
机构：
[1] Northwest Minzu Univ, Key Lab Chinas Natl Linguist Informat Technol, Lanzhou 730000, Peoples R China
来源：
ADVANCED HYBRID INFORMATION PROCESSING, PT I | 2022年 / 416卷
关键词：
Machine learning; Tibetan; Synthesis system; Signal extraction;
D O I：
10.1007/978-3-030-94551-0_37
中图分类号：
TP301 [理论、方法];
学科分类号：
081202 ;
摘要：
In order to improve the accuracy of Tibetan speech synthesis, a feature extraction method of Tibetan speech synthesis system based on machine learning is proposed. Based on the analysis of Tibetan speech text content, the construction of speech synthesis system is realized. By judging the level of Tibetan prosody, a synthetic encoder is designed to realize the feature extraction of Tibetan speech signal. According to the experimental results, under the condition of normal speaking speed and identical Tibetan speech content, the Tibetan speech synthesized by the speech signal feature extraction method of Tibetan speech synthesis system based on machine learning is more accurate.
引用
收藏
页码：470 / 479
页数：10
相关论文
共 50 条
  • [1] Method of speech signal feature extraction based on tensor decomposition model
    Yang, Li-Dong
    Wang, Jing
    Xie, Xiang
    Kuang, Jing-Ming
    Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology, 2013, 33 (11): : 1171 - 1175
  • [2] Feature extraction and classification efficiency analysis using machine learning approach for speech signal
    Singh, Mahesh K.
    MULTIMEDIA TOOLS AND APPLICATIONS, 2023, 83 (16) : 47069 - 47084
  • [3] Feature extraction and classification efficiency analysis using machine learning approach for speech signal
    Mahesh K. Singh
    Multimedia Tools and Applications, 2024, 83 : 47069 - 47084
  • [4] Dynamic Feature Extraction for Speech Signal Based on MUSIC
    Han Zhiyan
    Wang Jian
    PROCEEDINGS OF THE 28TH CHINESE CONTROL AND DECISION CONFERENCE (2016 CCDC), 2016, : 3770 - 3773
  • [5] Research on Tibetan Speech Endpoint Detection Method Based on Extreme Learning Machine
    Liu, Ze-guo
    ADVANCED HYBRID INFORMATION PROCESSING, PT I, 2022, 416 : 480 - 490
  • [6] A Study of Speech Feature Extraction Based on Manifold Learning
    Hao, Cheng
    Xin, Ma
    Xu, Yugong
    2018 INTERNATIONAL SYMPOSIUM ON POWER ELECTRONICS AND CONTROL ENGINEERING (ISPECE 2018), 2019, 1187
  • [7] A FEATURE FUSION METHOD BASED ON EXTREME LEARNING MACHINE FOR SPEECH EMOTION RECOGNITION
    Guo, Lili
    Wang, Longbiao
    Dang, Jianwu
    Zhang, Linjuan
    Guan, Haotian
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 2666 - 2670
  • [8] A robust feature extraction method based on CZCPA model for speech recognition system
    Zhang, XY
    Jiao, ZP
    Zhao, SY
    ICEMI 2005: Conference Proceedings of the Seventh International Conference on Electronic Measurement & Instruments, Vol 3, 2005, : 89 - 92
  • [9] Correlation Based Pitch Extraction Method in Speech Signal
    Hasan, Mirza A. F. M. Rashidul
    Yasmin, Rubaiyat
    Das, Dipankar
    Rahman, M. S.
    2014 9TH INTERNATIONAL FORUM ON STRATEGIC TECHNOLOGY (IFOST), 2014, : 140 - 143
  • [10] LPC AND LPCC METHOD OF FEATURE EXTRACTION IN SPEECH RECOGNITION SYSTEM
    Gupta, Harshita
    Gupta, Divya
    2016 6th International Conference - Cloud System and Big Data Engineering (Confluence), 2016, : 498 - 502
12345