HMM-based speech synthesis using sub-band basis spectrum model

Yamato Ohtani; Masatsune Tamura; Masahiro Morita; Takehiko Kagoshima; Masami Akamine

HMM-based speech synthesis using sub-band basis spectrum model

Yamato Ohtani, Masatsune Tamura, Masahiro Morita, Takehiko Kagoshima, Masami Akamine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose HMM-based text-to-speech (TTS) using sub-band basis spectrum model (SBM). SBM can represent vocal tract spectra and phase char-acteristics by a linear combination of sub-band basis vectors. Some reports suggest that analysis-synthesized speech based on SBM is close to natural speech and SBM can perform effectively in TTS. Therefore, the SBM framework is expected to have good effects on HMM-based TTS by improving speech quality. Subjective ex-perimental results show that the proposed method im-proves speech quality in some conditions.

Original language	English
Title of host publication	13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
Pages	1438-1441
Number of pages	4
Publication status	Published - 2012
Externally published	Yes
Event	13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 - Portland, OR, United States Duration: 2012 Sep 9 → 2012 Sep 13

Publication series

Name	13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
Volume	2

Conference

Conference	13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012
Country/Territory	United States
City	Portland, OR
Period	12/9/9 → 12/9/13

Keywords

Hidden Markov model
Phase feature
Speech synthesis
Sub-band basis spectrum model

ASJC Scopus subject areas

Computer Networks and Communications
Communication

Cite this

HMM-based speech synthesis using sub-band basis spectrum model. / Ohtani, Yamato; Tamura, Masatsune; Morita, Masahiro; Kagoshima, Takehiko; Akamine, Masami.

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. 2012. p. 1438-1441 (13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Ohtani, Y, Tamura, M, Morita, M, Kagoshima, T & Akamine, M 2012, HMM-based speech synthesis using sub-band basis spectrum model. in 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, vol. 2, pp. 1438-1441, 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, Portland, OR, United States, 12/9/9.

Ohtani, Yamato ; Tamura, Masatsune ; Morita, Masahiro ; Kagoshima, Takehiko ; Akamine, Masami. / HMM-based speech synthesis using sub-band basis spectrum model. 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012. 2012. pp. 1438-1441 (13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012).

@inproceedings{68298f4875234ebc9efbc3b25ac525ed,

title = "HMM-based speech synthesis using sub-band basis spectrum model",

abstract = "In this paper, we propose HMM-based text-to-speech (TTS) using sub-band basis spectrum model (SBM). SBM can represent vocal tract spectra and phase char-acteristics by a linear combination of sub-band basis vectors. Some reports suggest that analysis-synthesized speech based on SBM is close to natural speech and SBM can perform effectively in TTS. Therefore, the SBM framework is expected to have good effects on HMM-based TTS by improving speech quality. Subjective ex-perimental results show that the proposed method im-proves speech quality in some conditions.",

keywords = "Hidden Markov model, Phase feature, Speech synthesis, Sub-band basis spectrum model",

author = "Yamato Ohtani and Masatsune Tamura and Masahiro Morita and Takehiko Kagoshima and Masami Akamine",

note = "Copyright: Copyright 2013 Elsevier B.V., All rights reserved.; 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012 ; Conference date: 09-09-2012 Through 13-09-2012",

year = "2012",

language = "English",

isbn = "9781622767595",

series = "13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012",

pages = "1438--1441",

booktitle = "13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012",

}

TY - GEN

T1 - HMM-based speech synthesis using sub-band basis spectrum model

AU - Ohtani, Yamato

AU - Tamura, Masatsune

AU - Morita, Masahiro

AU - Kagoshima, Takehiko

AU - Akamine, Masami

PY - 2012

Y1 - 2012

N2 - In this paper, we propose HMM-based text-to-speech (TTS) using sub-band basis spectrum model (SBM). SBM can represent vocal tract spectra and phase char-acteristics by a linear combination of sub-band basis vectors. Some reports suggest that analysis-synthesized speech based on SBM is close to natural speech and SBM can perform effectively in TTS. Therefore, the SBM framework is expected to have good effects on HMM-based TTS by improving speech quality. Subjective ex-perimental results show that the proposed method im-proves speech quality in some conditions.

AB - In this paper, we propose HMM-based text-to-speech (TTS) using sub-band basis spectrum model (SBM). SBM can represent vocal tract spectra and phase char-acteristics by a linear combination of sub-band basis vectors. Some reports suggest that analysis-synthesized speech based on SBM is close to natural speech and SBM can perform effectively in TTS. Therefore, the SBM framework is expected to have good effects on HMM-based TTS by improving speech quality. Subjective ex-perimental results show that the proposed method im-proves speech quality in some conditions.

KW - Hidden Markov model

KW - Phase feature

KW - Speech synthesis

KW - Sub-band basis spectrum model

UR - http://www.scopus.com/inward/record.url?scp=84878389153&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878389153&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84878389153

SN - 9781622767595

T3 - 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

SP - 1438

EP - 1441

BT - 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

T2 - 13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Y2 - 9 September 2012 through 13 September 2012

ER -

HMM-based speech synthesis using sub-band basis spectrum model

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this