Enhancement of spectral clarity for HMM-based text-to-speech systems

Young Sun Joo, Chi Sang Jung, Hong-Goo Kang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper proposes a method to enhance the spectral clarity of hidden Markov model (HMM)-based text-to-speech (TTS) systems. A simple way of enhancing spectral clarity is increasing the order of spectral parameters in the speech analysis/synthesis stage, but the method has an inherent statistical modeling problem. The proposed algorithm takes a low-to-high-order spectral parameter mapping approach that adopts low-order parameters for HMM training but does high-order parameters for the actual synthesis step. Various ways of mapping criterion to find appropriate high-order parameters are investigated to further enhance the quality of synthesized speech. Performance evaluation results verify the superiority of the proposed method compared to the conventional one.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages7840-7843
Number of pages4
DOIs
Publication statusPublished - 2013 Oct 18
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: 2013 May 262013 May 31

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
CountryCanada
CityVancouver, BC
Period13/5/2613/5/31

Fingerprint

Hidden Markov models
Speech analysis

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Joo, Y. S., Jung, C. S., & Kang, H-G. (2013). Enhancement of spectral clarity for HMM-based text-to-speech systems. In 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings (pp. 7840-7843). [6639190] https://doi.org/10.1109/ICASSP.2013.6639190
Joo, Young Sun ; Jung, Chi Sang ; Kang, Hong-Goo. / Enhancement of spectral clarity for HMM-based text-to-speech systems. 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. 2013. pp. 7840-7843
@inproceedings{dd34a958062348e2af6ced29e92abf4f,
title = "Enhancement of spectral clarity for HMM-based text-to-speech systems",
abstract = "This paper proposes a method to enhance the spectral clarity of hidden Markov model (HMM)-based text-to-speech (TTS) systems. A simple way of enhancing spectral clarity is increasing the order of spectral parameters in the speech analysis/synthesis stage, but the method has an inherent statistical modeling problem. The proposed algorithm takes a low-to-high-order spectral parameter mapping approach that adopts low-order parameters for HMM training but does high-order parameters for the actual synthesis step. Various ways of mapping criterion to find appropriate high-order parameters are investigated to further enhance the quality of synthesized speech. Performance evaluation results verify the superiority of the proposed method compared to the conventional one.",
author = "Joo, {Young Sun} and Jung, {Chi Sang} and Hong-Goo Kang",
year = "2013",
month = "10",
day = "18",
doi = "10.1109/ICASSP.2013.6639190",
language = "English",
isbn = "9781479903566",
pages = "7840--7843",
booktitle = "2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings",

}

Joo, YS, Jung, CS & Kang, H-G 2013, Enhancement of spectral clarity for HMM-based text-to-speech systems. in 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings., 6639190, pp. 7840-7843, 2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013, Vancouver, BC, Canada, 13/5/26. https://doi.org/10.1109/ICASSP.2013.6639190

Enhancement of spectral clarity for HMM-based text-to-speech systems. / Joo, Young Sun; Jung, Chi Sang; Kang, Hong-Goo.

2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. 2013. p. 7840-7843 6639190.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Enhancement of spectral clarity for HMM-based text-to-speech systems

AU - Joo, Young Sun

AU - Jung, Chi Sang

AU - Kang, Hong-Goo

PY - 2013/10/18

Y1 - 2013/10/18

N2 - This paper proposes a method to enhance the spectral clarity of hidden Markov model (HMM)-based text-to-speech (TTS) systems. A simple way of enhancing spectral clarity is increasing the order of spectral parameters in the speech analysis/synthesis stage, but the method has an inherent statistical modeling problem. The proposed algorithm takes a low-to-high-order spectral parameter mapping approach that adopts low-order parameters for HMM training but does high-order parameters for the actual synthesis step. Various ways of mapping criterion to find appropriate high-order parameters are investigated to further enhance the quality of synthesized speech. Performance evaluation results verify the superiority of the proposed method compared to the conventional one.

AB - This paper proposes a method to enhance the spectral clarity of hidden Markov model (HMM)-based text-to-speech (TTS) systems. A simple way of enhancing spectral clarity is increasing the order of spectral parameters in the speech analysis/synthesis stage, but the method has an inherent statistical modeling problem. The proposed algorithm takes a low-to-high-order spectral parameter mapping approach that adopts low-order parameters for HMM training but does high-order parameters for the actual synthesis step. Various ways of mapping criterion to find appropriate high-order parameters are investigated to further enhance the quality of synthesized speech. Performance evaluation results verify the superiority of the proposed method compared to the conventional one.

UR - http://www.scopus.com/inward/record.url?scp=84890460040&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890460040&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2013.6639190

DO - 10.1109/ICASSP.2013.6639190

M3 - Conference contribution

AN - SCOPUS:84890460040

SN - 9781479903566

SP - 7840

EP - 7843

BT - 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings

ER -

Joo YS, Jung CS, Kang H-G. Enhancement of spectral clarity for HMM-based text-to-speech systems. In 2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings. 2013. p. 7840-7843. 6639190 https://doi.org/10.1109/ICASSP.2013.6639190