A hybrid model for speech synthesis

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

4 Citations (Scopus)

Abstract

A hybrid model for speech analysis/synthesis is proposed. It relies on a time-varying autoregressive moving-average (ARMA) model and the short-time Fourier transform (STFT). The model is hybrid in that the periodic (narrowband) component in speech is represented in the frequency domain by a harmonic-based STFT, while the random component in speech is represented by a random noise sequence, appropriately shaped by the ARMA model. The time-varying ARMA model has a dual function (namely, it creates a spectral envelope that fits accurately the harmonic STFT components) and provides for the spectral shaping of random noise. This hybrid model essentially incorporates the benefits of waveform coders by employing the STFT and the benefits of traditional vocoders by using an appropriately shaped noise sequence; thus, it is expected to yield robust speech synthesis at low data rates.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
PublisherPubl by IEEE
Pages1521-1524
Number of pages4
Volume2
StatePublished - 1990
Event1990 IEEE International Symposium on Circuits and Systems Part 3 (of 4) - New Orleans, LA, USA
Duration: May 1 1990May 3 1990

Other

Other1990 IEEE International Symposium on Circuits and Systems Part 3 (of 4)
CityNew Orleans, LA, USA
Period5/1/905/3/90

Fingerprint

Speech synthesis
Fourier transforms
Vocoders
Speech analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Spanias, A. (1990). A hybrid model for speech synthesis. In Proceedings - IEEE International Symposium on Circuits and Systems (Vol. 2, pp. 1521-1524). Publ by IEEE.

A hybrid model for speech synthesis. / Spanias, Andreas.

Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 2 Publ by IEEE, 1990. p. 1521-1524.

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

Spanias, A 1990, A hybrid model for speech synthesis. in Proceedings - IEEE International Symposium on Circuits and Systems. vol. 2, Publ by IEEE, pp. 1521-1524, 1990 IEEE International Symposium on Circuits and Systems Part 3 (of 4), New Orleans, LA, USA, 5/1/90.
Spanias A. A hybrid model for speech synthesis. In Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 2. Publ by IEEE. 1990. p. 1521-1524
Spanias, Andreas. / A hybrid model for speech synthesis. Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 2 Publ by IEEE, 1990. pp. 1521-1524
@inproceedings{55eaf348bd684795997434949afcc52d,
title = "A hybrid model for speech synthesis",
abstract = "A hybrid model for speech analysis/synthesis is proposed. It relies on a time-varying autoregressive moving-average (ARMA) model and the short-time Fourier transform (STFT). The model is hybrid in that the periodic (narrowband) component in speech is represented in the frequency domain by a harmonic-based STFT, while the random component in speech is represented by a random noise sequence, appropriately shaped by the ARMA model. The time-varying ARMA model has a dual function (namely, it creates a spectral envelope that fits accurately the harmonic STFT components) and provides for the spectral shaping of random noise. This hybrid model essentially incorporates the benefits of waveform coders by employing the STFT and the benefits of traditional vocoders by using an appropriately shaped noise sequence; thus, it is expected to yield robust speech synthesis at low data rates.",
author = "Andreas Spanias",
year = "1990",
language = "English (US)",
volume = "2",
pages = "1521--1524",
booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - A hybrid model for speech synthesis

AU - Spanias, Andreas

PY - 1990

Y1 - 1990

N2 - A hybrid model for speech analysis/synthesis is proposed. It relies on a time-varying autoregressive moving-average (ARMA) model and the short-time Fourier transform (STFT). The model is hybrid in that the periodic (narrowband) component in speech is represented in the frequency domain by a harmonic-based STFT, while the random component in speech is represented by a random noise sequence, appropriately shaped by the ARMA model. The time-varying ARMA model has a dual function (namely, it creates a spectral envelope that fits accurately the harmonic STFT components) and provides for the spectral shaping of random noise. This hybrid model essentially incorporates the benefits of waveform coders by employing the STFT and the benefits of traditional vocoders by using an appropriately shaped noise sequence; thus, it is expected to yield robust speech synthesis at low data rates.

AB - A hybrid model for speech analysis/synthesis is proposed. It relies on a time-varying autoregressive moving-average (ARMA) model and the short-time Fourier transform (STFT). The model is hybrid in that the periodic (narrowband) component in speech is represented in the frequency domain by a harmonic-based STFT, while the random component in speech is represented by a random noise sequence, appropriately shaped by the ARMA model. The time-varying ARMA model has a dual function (namely, it creates a spectral envelope that fits accurately the harmonic STFT components) and provides for the spectral shaping of random noise. This hybrid model essentially incorporates the benefits of waveform coders by employing the STFT and the benefits of traditional vocoders by using an appropriately shaped noise sequence; thus, it is expected to yield robust speech synthesis at low data rates.

UR - http://www.scopus.com/inward/record.url?scp=0025592604&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0025592604&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0025592604

VL - 2

SP - 1521

EP - 1524

BT - Proceedings - IEEE International Symposium on Circuits and Systems

PB - Publ by IEEE

ER -