A method for voice conversion based on viterbi algorithm

被引：0
|
作者：
Jian, Zhi-Hua [1 ,2 ]
Yang, Zhen [2 ]
机构：
[1] School of Communication Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, China
[2] School of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu 210003, China
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2009年 / 37卷 / 07期
关键词：
Viterbi algorithm;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
A novel method for voice conversion based on Viterbi algorithm is proposed in this paper. This method uses the matrix of transition probabilities of the target speaker' frames to represent the timing information of the speech sequence, and then determines the most appropriate component of the GMM by utilizing the Viterbi algorithm for converting each frame of the source speech. It avoids the spectral discontinuities caused by losing the relationship between the adjacent speech frames, and alleviates the spectral smoothing due to the weighted averaging in the traditional GMM-based algorithms and then enhances the formant. Both objective and subjective evaluation's results have demonstrated that the proposed method improves the performance of the conventional voice conversion system based on GMM.
引用
收藏
页码：1470 / 1475
相关论文
共 50 条
  • [41] Design of a decoder error corrector based on VITERBI algorithm
    Arich, T
    Mohssine, M
    Zenkouar, L
    ICM 2002: 14TH INTERNATIONAL CONFERENCE ON MICROELECTRONICS, 2002, : 161 - 164
  • [42] An improved spectral and prosodic transformation method in straight-based voice conversion
    Qin, L
    Chen, GP
    Ling, ZH
    Dai, LR
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 21 - 24
  • [43] Estimation method of glottal vocal efficiency based on conversion function　of　voice　source
    ZOU Yuan WAN Mingxi ZHAO Shouguo WANG Supin(1 Department of Biomedical Engineering
    ChineseJournalofAcoustics, 2002, (04) : 332 - 342
  • [44] Improving Segmental GMM Based Voice Conversion Method with Target Frame Selection
    Gu, Hung-Yan
    Tsai, Sung-Fung
    2014 9TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2014, : 483 - 487
  • [45] A novel method for prosody prediction in voice conversion
    Helander, Elina E.
    Nurminen, Jani
    2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 509 - +
  • [46] STATISTICAL VOICE CONVERSION BASED ON WAVENET
    Niwa, Jumpei
    Yoshimura, Takenori
    Hashimoto, Kei
    Oura, Keiichiro
    Nankaku, Yoshihiko
    Tokuda, Keiichi
    2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5289 - 5293
  • [47] VTLN-based voice conversion
    Sündermann, D
    Ney, H
    PROCEEDINGS OF THE 3RD IEEE INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND INFORMATION TECHNOLOGY, 2003, : 556 - 559
  • [48] A New Robust Voice Activity Detection method based on Genetic Algorithm
    Farsinejad, M.
    Analoui, M.
    ATNAC: 2008 AUSTRALASIAN TELECOMMUNICATION NETWOKS AND APPLICATIONS CONFERENCE, 2008, : 80 - 84
  • [49] Constrained Viterbi algorithm and Viterbi algorithm performance comparison over AWGN and BSC
    Zhou Ting
    Xu Ming
    Chen Dongxia
    Yu Lun
    ICCSE'2006: Proceedings of the First International Conference on Computer Science & Education: ADVANCED COMPUTER TECHNOLOGY, NEW EDUCATION, 2006, : 708 - 711
  • [50] Controllable voice conversion based on quantization of voice factor scores
    Isako, Takumi
    Onishi, Kotaro
    Kishida, Takuya
    Nakashika, Toru
    PROCEEDINGS OF 2022 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2022, : 1444 - 1448
12345