Presentation 2019-03-15
[Poster Presentation] F0 estimation using TV-CAR speech analysis based on Regularized LP
Keiichi Funaki,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Linear Prediction (LP) analysis is speech analysis to estimate AR(Auto-Regressive) coefficients to represent the all-pole spectrum that is based on speech coding and recently is applied also in speech synthesis. Wehave proposed TV-CAR(Time-Varying Complex AR) speech analysis and have applied it into the speech processingsuch as robust ASR or F0 estimation of speech. We have proposed l2-norm optimization-based TV-CAR speechanalysis for an analytic signal that includes MMSE(Minimizing Mean Square Error) or ELS(Extended Least Square) method. On the other hand, B.Kleijn et al. have proposed a Regularized Linear Prediction (RLP) method. In theRLP, l2 regularized term that means spectral variant in the frequencies to avoid pitch related bias is introduced. The parameter is estimated so as to minimize the l2-norm criterion added by the l2-regularized penalty term. Moreover, P.Alku et al. have proposed Time-Regularized LP (TRLP) analysis. In the TRLP, the regularized term is set as thel2-norm of the difference between the current parameters and previous ones. In this paper, the RLP-based TV-CARspeech analysis is proposed and evaluated with the F0 estimation of speech using IRAPT.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Time-Varying Complex AR(TV-CAR) analysis / Analytic signal / l2-norm regularization / F0 estimation of speech / IRAPT
Paper # EA2018-152,SIP2018-158,SP2018-114
Date of Issue 2019-03-07 (EA, SIP, SP)

Conference Information
Committee EA / SIP / SP
Conference Date 2019/3/14(2days)
Place (in Japanese) (See Japanese page)
Place (in English) i+Land nagasaki (Nagasaki-shi)
Topics (in Japanese) (See Japanese page)
Topics (in English) Engineering/Electro Acoustics, Signal Processing, Speech, and Related Topics
Chair Suehiro Shimauchi(Kanazawa Inst. of Tech.) / Shogo Muramatsu(Niigata Univ.) / Yoichi Yamashita(Ritsumeikan Univ.)
Vice Chair Kenichi Furuya(Oita Univ.) / Kanji Watanabe(Akita Pref. Univ.) / Naoyuki Aikawa(TUS) / Kazunori Hayashi(Osaka City Univ) / Akinobu Ri(Nagoya Inst. of Tech.)
Secretary Kenichi Furuya(Shizuoka Inst. of Science and Tech.) / Kanji Watanabe(NHK) / Naoyuki Aikawa(Takushoku Univ.) / Kazunori Hayashi(Hiroshima Univ.) / Akinobu Ri(Kyoto Univ.)
Assistant Keisuke Imoto(Ritsumeikan Univ.) / Daisuke Morikawa(Toyama Pref Univ.) / Katsumi Konishi(Hosei Univ.) / hyihsin(Takushoku Univ.) / Tomoki Koriyama(Tokyo Inst. of Tech.) / Satoshi Kobashikawa(NTT)

Paper Information
Registration To Technical Committee on Engineering Acoustics / Technical Committee on Signal Processing / Technical Committee on Speech
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Poster Presentation] F0 estimation using TV-CAR speech analysis based on Regularized LP
Sub Title (in English)
Keyword(1) Time-Varying Complex AR(TV-CAR) analysis
Keyword(2) Analytic signal
Keyword(3) l2-norm regularization
Keyword(4) F0 estimation of speech
Keyword(5) IRAPT
1st Author's Name Keiichi Funaki
1st Author's Affiliation Univrsity of the Ryukyus(Univ. of the Ryukyus)
Date 2019-03-15
Paper # EA2018-152,SIP2018-158,SP2018-114
Volume (vol) vol.118
Number (no) EA-495,SIP-496,SP-497
Page pp.pp.311-316(EA), pp.311-316(SIP), pp.311-316(SP),
#Pages 6
Date of Issue 2019-03-07 (EA, SIP, SP)