High Quality Speech Synthesis System Based on Waveform Concatenation of Phoneme Segment

Tomohisa HIROKAWA; Kenzo ITOH; Hirokazu SATO

High Quality Speech Synthesis System Based on Waveform Concatenation of Phoneme Segment

Tomohisa HIROKAWA, Kenzo ITOH, Hirokazu SATO

Full Text Views

0

Cite this

Summary :

A new system for speech synthesis by concatenating waveforms selected from a dictionary is described. The dictionary is constructed from a two-hour speech that includes isolated words and sentences uttered by one male speaker, and contains over 45,000 entries which are identified by their average pitch, dynamic pitch parameter which represents micro pitch structure in a segment, duration and average amplitude. Phoneme duration is set according to phoneme environment, and phoneme power is controlled, by both pitch frequency and phoneme environment. Tests show the average errors in vowel duration and consonant duration are 28.8 ms and 16.8 ms respectively, and the vowel power average error is 2.9 dB. The pitch frequency patterns are calculated according to a conventional model in which the accent component is abbed to a gross phrase component. Set a phoneme string and prosody information, the optimum waveforms are selected from the dictionary by matching their attributes with the given phonetic and prosodic information. A waveform selection function, which has two terms corresponding to prosody and phonological coincidence between rule-set values and waveform values from the dictionary, is proposed. The weight coefficients used in the selection function are determined through subjective hearing tests. The selected waveform segments are then modified in waveform domain to further adjust for the desired prosody. A pitch frequency modification method based on pitch synchronous overlap-add technique is introduced into the system. Lastly, the waveforms are interpolated between voiced waveforms to avoid abrupt changes in voice spectrum and waveform shape. An absolute evaluation test of five grades is performed to the synthesized voice and the mean of the score is 3.1, which is over "good," and while the original speaker quality is retained.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E76-A No.11 pp.1964-1970

Publication Date: 1993/11/25

Publicized

Online ISSN

DOI

Type of Manuscript: Special Section PAPER (Special Section on Speech Synthesis: Current Technologies and Thier Application)

Category

Cite this

Copy

Tomohisa HIROKAWA, Kenzo ITOH, Hirokazu SATO, "High Quality Speech Synthesis System Based on Waveform Concatenation of Phoneme Segment" in IEICE TRANSACTIONS on Fundamentals, vol. E76-A, no. 11, pp. 1964-1970, November 1993, doi: .
Abstract: A new system for speech synthesis by concatenating waveforms selected from a dictionary is described. The dictionary is constructed from a two-hour speech that includes isolated words and sentences uttered by one male speaker, and contains over 45,000 entries which are identified by their average pitch, dynamic pitch parameter which represents micro pitch structure in a segment, duration and average amplitude. Phoneme duration is set according to phoneme environment, and phoneme power is controlled, by both pitch frequency and phoneme environment. Tests show the average errors in vowel duration and consonant duration are 28.8 ms and 16.8 ms respectively, and the vowel power average error is 2.9 dB. The pitch frequency patterns are calculated according to a conventional model in which the accent component is abbed to a gross phrase component. Set a phoneme string and prosody information, the optimum waveforms are selected from the dictionary by matching their attributes with the given phonetic and prosodic information. A waveform selection function, which has two terms corresponding to prosody and phonological coincidence between rule-set values and waveform values from the dictionary, is proposed. The weight coefficients used in the selection function are determined through subjective hearing tests. The selected waveform segments are then modified in waveform domain to further adjust for the desired prosody. A pitch frequency modification method based on pitch synchronous overlap-add technique is introduced into the system. Lastly, the waveforms are interpolated between voiced waveforms to avoid abrupt changes in voice spectrum and waveform shape. An absolute evaluation test of five grades is performed to the synthesized voice and the mean of the score is 3.1, which is over "good," and while the original speaker quality is retained.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e76-a_11_1964/_p

Copy

@ARTICLE{e76-a_11_1964,
author={Tomohisa HIROKAWA, Kenzo ITOH, Hirokazu SATO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={High Quality Speech Synthesis System Based on Waveform Concatenation of Phoneme Segment},
year={1993},
volume={E76-A},
number={11},
pages={1964-1970},
abstract={A new system for speech synthesis by concatenating waveforms selected from a dictionary is described. The dictionary is constructed from a two-hour speech that includes isolated words and sentences uttered by one male speaker, and contains over 45,000 entries which are identified by their average pitch, dynamic pitch parameter which represents micro pitch structure in a segment, duration and average amplitude. Phoneme duration is set according to phoneme environment, and phoneme power is controlled, by both pitch frequency and phoneme environment. Tests show the average errors in vowel duration and consonant duration are 28.8 ms and 16.8 ms respectively, and the vowel power average error is 2.9 dB. The pitch frequency patterns are calculated according to a conventional model in which the accent component is abbed to a gross phrase component. Set a phoneme string and prosody information, the optimum waveforms are selected from the dictionary by matching their attributes with the given phonetic and prosodic information. A waveform selection function, which has two terms corresponding to prosody and phonological coincidence between rule-set values and waveform values from the dictionary, is proposed. The weight coefficients used in the selection function are determined through subjective hearing tests. The selected waveform segments are then modified in waveform domain to further adjust for the desired prosody. A pitch frequency modification method based on pitch synchronous overlap-add technique is introduced into the system. Lastly, the waveforms are interpolated between voiced waveforms to avoid abrupt changes in voice spectrum and waveform shape. An absolute evaluation test of five grades is performed to the synthesized voice and the mean of the score is 3.1, which is over "good," and while the original speaker quality is retained.},
keywords={},
doi={},
ISSN={},
month={November},}

Copy

TY - JOUR
TI - High Quality Speech Synthesis System Based on Waveform Concatenation of Phoneme Segment
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1964
EP - 1970
AU - Tomohisa HIROKAWA
AU - Kenzo ITOH
AU - Hirokazu SATO
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E76-A
IS - 11
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - November 1993
AB - A new system for speech synthesis by concatenating waveforms selected from a dictionary is described. The dictionary is constructed from a two-hour speech that includes isolated words and sentences uttered by one male speaker, and contains over 45,000 entries which are identified by their average pitch, dynamic pitch parameter which represents micro pitch structure in a segment, duration and average amplitude. Phoneme duration is set according to phoneme environment, and phoneme power is controlled, by both pitch frequency and phoneme environment. Tests show the average errors in vowel duration and consonant duration are 28.8 ms and 16.8 ms respectively, and the vowel power average error is 2.9 dB. The pitch frequency patterns are calculated according to a conventional model in which the accent component is abbed to a gross phrase component. Set a phoneme string and prosody information, the optimum waveforms are selected from the dictionary by matching their attributes with the given phonetic and prosodic information. A waveform selection function, which has two terms corresponding to prosody and phonological coincidence between rule-set values and waveform values from the dictionary, is proposed. The weight coefficients used in the selection function are determined through subjective hearing tests. The selected waveform segments are then modified in waveform domain to further adjust for the desired prosody. A pitch frequency modification method based on pitch synchronous overlap-add technique is introduced into the system. Lastly, the waveforms are interpolated between voiced waveforms to avoid abrupt changes in voice spectrum and waveform shape. An absolute evaluation test of five grades is performed to the synthesized voice and the mean of the score is 3.1, which is over "good," and while the original speaker quality is retained.
ER -