JAIST Repository >
School of Information Science >
Conference Papers >
Conference Papers >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10119/13489

Title: A study on quality improvement of HMM-based synthesized voices using asymmetric bilinear model
Authors: Dinh-Anh, Tuan
Morikawa, Daisuke
Akagi, Masato
Issue Date: 2016-03
Publisher: 信号処理学会
Magazine name: 2016 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'16)
Start page: 13
End page: 16
Abstract: HMM-based synthesized voices are intelligible but not natural especially in limited data condition because of over smoothing speech spectra in time-frequency domain. Improving naturalness is a critical problem of HMM-based speech synthesis. One solution for the problem is using voice conversion techniques to convert over-smoothed spectra to natural spectra. Although conventional conversion techniques transform speech spectra to natural ones to improve naturalness, they cause unexpected distortions on acceptable intelligibility of synthesized speech. The aim of the paper is to improve naturalness without violating intelligibility of synthesized speech employing an asymmetric bilinear model (ABM) to separate intelligibility and naturalness. In the paper, an ABM was implemented on modulation spectrum domain of Mel-cepstral coefficient (MCC) sequence to enhance fine structure of spectral parameter trajectory generated from HMMs. Subjective evaluations carried out on English data confirm that the achieved naturalness of proposed method is competitive with other methods in large data condition and outperform other methods in limited data condition. Moreover, modified rhyme test (MRT) shows that acceptable intelligibility of synthesized speech is well-preserved with proposed method.
Rights: Copyright (C) 2016 信号処理学会. Tuan Dinh-Anh, Daisuke Morikawa, Masato Akagi, 2016 RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'16), 2016, 13-16.
URI: http://hdl.handle.net/10119/13489
Material Type: publisher
Appears in Collections:b11-1. 会議発表論文・発表資料 (Conference Papers)

Files in This Item:

File Description SizeFormat
NCSP2016_Dinh.pdf866KbAdobe PDFView/Open

All items in DSpace are protected by copyright, with all rights reserved.


Contact : Library Information Section, Japan Advanced Institute of Science and Technology