Sub-band text-to-speech combining sample-based spectrum with statistically generated spectrum

Tadashi Inai; Sunao Hara; Masanobu Abe; Yusuke Ijima; Noboru Miyazaki; Hideyuki Mizuno

Sub-band text-to-speech combining sample-based spectrum with statistically generated spectrum

Tadashi Inai, Sunao Hara, Masanobu Abe, Yusuke Ijima, Noboru Miyazaki, Hideyuki Mizuno

Research output: Contribution to journal › Conference article › peer-review

Abstract

As described in this paper, we propose a sub-band speech syn- thesis approach to develop a high quality Text-to-Speech (TTS) system: A sample-based spectrum is used in the high-frequency band and spectrum generated by HMM-based TTS is used in the low-frequency band. Herein, sample-based spectrum means spectrum selected from a phoneme database such that it is the most similar to spectrum generated by HMM-based speech syn- thesis. A key idea is to compensate over-smoothing caused by statistical procedures by introducing a sample-based spectrum, especially in the high-frequency band. Listening test results show that the proposed method has better performance than HMM-based speech synthesis in terms of clarity. It is at the same level as HMM-based speech synthesis in terms of smooth- ness. In addition, preference test results among the proposed method, HMM-based speech synthesis, and waveform speech synthesis using 80 min speech data reveal that the proposed method is the most liked.

Original language	English
Pages (from-to)	264-268
Number of pages	5
Journal	Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume	2015-January
Publication status	Published - 2015
Event	16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 - Dresden, Germany Duration: Sept 6 2015 → Sept 10 2015

Keywords

HMM-based speech synthesis
Sub-band
Waveform-based speech synthesis

ASJC Scopus subject areas

Language and Linguistics
Human-Computer Interaction
Signal Processing
Software
Modelling and Simulation

Cite this

Sub-band text-to-speech combining sample-based spectrum with statistically generated spectrum. / Inai, Tadashi; Hara, Sunao ; Abe, Masanobu et al.
In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH, Vol. 2015-January, 2015, p. 264-268.

Research output: Contribution to journal › Conference article › peer-review

@article{abcf8870f18946b5b772cde1885499ba,

title = "Sub-band text-to-speech combining sample-based spectrum with statistically generated spectrum",

abstract = "As described in this paper, we propose a sub-band speech syn- thesis approach to develop a high quality Text-to-Speech (TTS) system: A sample-based spectrum is used in the high-frequency band and spectrum generated by HMM-based TTS is used in the low-frequency band. Herein, sample-based spectrum means spectrum selected from a phoneme database such that it is the most similar to spectrum generated by HMM-based speech syn- thesis. A key idea is to compensate over-smoothing caused by statistical procedures by introducing a sample-based spectrum, especially in the high-frequency band. Listening test results show that the proposed method has better performance than HMM-based speech synthesis in terms of clarity. It is at the same level as HMM-based speech synthesis in terms of smooth- ness. In addition, preference test results among the proposed method, HMM-based speech synthesis, and waveform speech synthesis using 80 min speech data reveal that the proposed method is the most liked.",

keywords = "HMM-based speech synthesis, Sub-band, Waveform-based speech synthesis",

author = "Tadashi Inai and Sunao Hara and Masanobu Abe and Yusuke Ijima and Noboru Miyazaki and Hideyuki Mizuno",

note = "Publisher Copyright: Copyright {\textcopyright} 2015 ISCA.; 16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 ; Conference date: 06-09-2015 Through 10-09-2015",

year = "2015",

language = "English",

volume = "2015-January",

pages = "264--268",

journal = "Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH",

issn = "2308-457X",

}

TY - JOUR

T1 - Sub-band text-to-speech combining sample-based spectrum with statistically generated spectrum

AU - Inai, Tadashi

AU - Hara, Sunao

AU - Abe, Masanobu

AU - Ijima, Yusuke

AU - Miyazaki, Noboru

AU - Mizuno, Hideyuki

PY - 2015

Y1 - 2015

N2 - As described in this paper, we propose a sub-band speech syn- thesis approach to develop a high quality Text-to-Speech (TTS) system: A sample-based spectrum is used in the high-frequency band and spectrum generated by HMM-based TTS is used in the low-frequency band. Herein, sample-based spectrum means spectrum selected from a phoneme database such that it is the most similar to spectrum generated by HMM-based speech syn- thesis. A key idea is to compensate over-smoothing caused by statistical procedures by introducing a sample-based spectrum, especially in the high-frequency band. Listening test results show that the proposed method has better performance than HMM-based speech synthesis in terms of clarity. It is at the same level as HMM-based speech synthesis in terms of smooth- ness. In addition, preference test results among the proposed method, HMM-based speech synthesis, and waveform speech synthesis using 80 min speech data reveal that the proposed method is the most liked.

AB - As described in this paper, we propose a sub-band speech syn- thesis approach to develop a high quality Text-to-Speech (TTS) system: A sample-based spectrum is used in the high-frequency band and spectrum generated by HMM-based TTS is used in the low-frequency band. Herein, sample-based spectrum means spectrum selected from a phoneme database such that it is the most similar to spectrum generated by HMM-based speech syn- thesis. A key idea is to compensate over-smoothing caused by statistical procedures by introducing a sample-based spectrum, especially in the high-frequency band. Listening test results show that the proposed method has better performance than HMM-based speech synthesis in terms of clarity. It is at the same level as HMM-based speech synthesis in terms of smooth- ness. In addition, preference test results among the proposed method, HMM-based speech synthesis, and waveform speech synthesis using 80 min speech data reveal that the proposed method is the most liked.

KW - HMM-based speech synthesis

KW - Sub-band

KW - Waveform-based speech synthesis

UR - http://www.scopus.com/inward/record.url?scp=84959169493&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84959169493&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84959169493

SN - 2308-457X

VL - 2015-January

SP - 264

EP - 268

JO - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

JF - Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

T2 - 16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015

Y2 - 6 September 2015 through 10 September 2015

ER -

Sub-band text-to-speech combining sample-based spectrum with statistically generated spectrum

Abstract

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this