Waveform interpolation-based speech analysis/synthesis for HMM-based TTS systems

Chi Sang Jung; Young Sun Joo; Hong Goo Kang

doi:10.1109/LSP.2012.2221703

Waveform interpolation-based speech analysis/synthesis for HMM-based TTS systems

Chi Sang Jung, Young Sun Joo, Hong Goo Kang

Department of Electrical and Electronic Engineering

Research output: Contribution to journal › Article

10 Citations (Scopus)

Abstract

This letter proposes an HMM-based Text-to-Speech (TTS) system using waveform interpolation (WI)-based speech analysis and synthesis. The synthesized speech quality of the proposed system is significantly improved due to adopting an enhanced excitation modeling technique. The decomposition of characteristic waveform (CW) into slowly evolving waveform (SEW) and rapidly evolving waveform (REW) is efficient not only for excitation modeling but also for training process of HMMs. Objective and subjective test results verify the superiority of the proposed approach to conventional ones.

Original language	English
Article number	6319353
Pages (from-to)	809-812
Number of pages	4
Journal	IEEE Signal Processing Letters
Volume	19
Issue number	12
DOIs	https://doi.org/10.1109/LSP.2012.2221703
Publication status	Published - 2012 Oct 29

Fingerprint

All Science Journal Classification (ASJC) codes

Signal Processing
Electrical and Electronic Engineering
Applied Mathematics

Cite this

Jung, C. S., Joo, Y. S., & Kang, H. G. (2012). Waveform interpolation-based speech analysis/synthesis for HMM-based TTS systems. IEEE Signal Processing Letters, 19(12), 809-812. [6319353]. https://doi.org/10.1109/LSP.2012.2221703

@article{89264f45127740ef858b0da94d1f8596,

title = "Waveform interpolation-based speech analysis/synthesis for HMM-based TTS systems",

abstract = "This letter proposes an HMM-based Text-to-Speech (TTS) system using waveform interpolation (WI)-based speech analysis and synthesis. The synthesized speech quality of the proposed system is significantly improved due to adopting an enhanced excitation modeling technique. The decomposition of characteristic waveform (CW) into slowly evolving waveform (SEW) and rapidly evolving waveform (REW) is efficient not only for excitation modeling but also for training process of HMMs. Objective and subjective test results verify the superiority of the proposed approach to conventional ones.",

author = "Jung, {Chi Sang} and Joo, {Young Sun} and Kang, {Hong Goo}",

year = "2012",

month = oct

day = "29",

doi = "10.1109/LSP.2012.2221703",

language = "English",

volume = "19",

pages = "809--812",

journal = "IEEE Signal Processing Letters",

issn = "1070-9908",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "12",

}

TY - JOUR

T1 - Waveform interpolation-based speech analysis/synthesis for HMM-based TTS systems

AU - Jung, Chi Sang

AU - Joo, Young Sun

AU - Kang, Hong Goo

PY - 2012/10/29

Y1 - 2012/10/29

N2 - This letter proposes an HMM-based Text-to-Speech (TTS) system using waveform interpolation (WI)-based speech analysis and synthesis. The synthesized speech quality of the proposed system is significantly improved due to adopting an enhanced excitation modeling technique. The decomposition of characteristic waveform (CW) into slowly evolving waveform (SEW) and rapidly evolving waveform (REW) is efficient not only for excitation modeling but also for training process of HMMs. Objective and subjective test results verify the superiority of the proposed approach to conventional ones.

AB - This letter proposes an HMM-based Text-to-Speech (TTS) system using waveform interpolation (WI)-based speech analysis and synthesis. The synthesized speech quality of the proposed system is significantly improved due to adopting an enhanced excitation modeling technique. The decomposition of characteristic waveform (CW) into slowly evolving waveform (SEW) and rapidly evolving waveform (REW) is efficient not only for excitation modeling but also for training process of HMMs. Objective and subjective test results verify the superiority of the proposed approach to conventional ones.

UR - http://www.scopus.com/inward/record.url?scp=84867829093&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867829093&partnerID=8YFLogxK

U2 - 10.1109/LSP.2012.2221703

DO - 10.1109/LSP.2012.2221703

M3 - Article

AN - SCOPUS:84867829093

VL - 19

SP - 809

EP - 812

JO - IEEE Signal Processing Letters

JF - IEEE Signal Processing Letters

SN - 1070-9908

IS - 12

M1 - 6319353

ER -

Access to Document

10.1109/LSP.2012.2221703