Funaki Keiichi

写真a

Title

Lecturer

Researcher Number(JSPS Kakenhi)

30315486
To the head of this page.▲

Current Affiliation Organization 【 display / non-display 】

  • Duty   University of the Ryukyus   Abolition organization   Computing and Networking Center   Lecturer  

To the head of this page.▲

Academic degree 【 display / non-display 】

  • Hokkaido University -  Doctor of Engineering

To the head of this page.▲

External Career 【 display / non-display 】

  • 1988.04
    -
    1996.03

    NEC Corp.  

  • 1999.04
    　
    　

    University of the Ryukyus, Computing and Networking Center, Assistant Professor  

To the head of this page.▲

Research Interests 【 display / non-display 】

  • Information Engineering,Communication Engineering

  • 音声符号化

  • 音声合成

  • 音声認識）,複素信号処理,情報工学

To the head of this page.▲

Research Theme 【 display / non-display 】

  • Digital Water Marking

  • Speech Information Processing

  • Speech Signal Processing

To the head of this page.▲

Thesis 【 display / non-display 】

  • Speech Analysis Methods Based on Accurate Models

    1999.03

To the head of this page.▲

Published Papers 【 display / non-display 】

  • Sparse Time-Varying Complex AR(TV-CAR) speech analysis based on Adaptive LASSO

    舟木　慶一

    IEICE, Trans. on Fundamentals   E102-A ( 12 )   2019.12

    Type of publication: Research paper (scientific journal)

  • TV-CAR speech analysis based on Regularized LP

    Funaki K.

    European Signal Processing Conference ( European Signal Processing Conference )  2019-September   2019.09 [ Peer Review Accepted ]

    Type of publication: Research paper (scientific journal)

    • Access this article
      DOI

  • Sparse Time-Varying Complex AR (TV-CAR) Speech Analysis Based on Adaptive LASSO

    FUNAKI Keiichi

    IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences ( 一般社団法人 電子情報通信学会 )  102 ( 12 ) 1910 - 1914   2019 [ Peer Review Accepted ]

    Type of publication: Research paper (scientific journal)

    　View Summary

    <p>Linear Prediction (LP) analysis is commonly used in speech processing. LP is based on Auto-Regressive (AR) model and it estimates the AR model parameter from signals with <i>l</i><sub>2</sub>-norm optimization. Recently, sparse estimation is paid attention since it can extract significant features from big data. The sparse estimation is realized by <i>l</i><sub>1</sub> or <i>l</i><sub>0</sub>-norm optimization or regularization. Sparse LP analysis methods based on <i>l</i><sub>1</sub>-norm optimization have been proposed. Since excitation of speech is not white Gaussian, a sparse LP estimation can estimate more accurate parameter than the conventional <i>l</i><sub>2</sub>-norm based LP. These are time-invariant and real-valued analysis. We have been studied Time-Varying Complex AR (TV-CAR) analysis for an analytic signal and have evaluated the performance on speech processing. The TV-CAR methods are <i>l</i><sub>2</sub>-norm methods. In this paper, we propose the sparse TV-CAR analysis based on adaptive LASSO (Least absolute shrinkage and selection operator) that is <i>l</i><sub>1</sub>-norm regularization and evaluate the performance on <i>F</i><sub>0</sub> estimation of speech using IRAPT (Instantaneous RAPT). The experimental results show that the sparse TV-CAR methods perform better for a high level of additive Pink noise.</p>

    • Access this article
      DOI

  • TV-CAR speech analysis based on Regularized LP.

    Keiichi Funaki

    27th European Signal Processing Conference, EUSIPCO 2019, A Coruña, Spain, September 2-6, 2019 ( IEEE )    1 - 5   2019

    Type of publication: Research paper (scientific journal)

  • F0 Estimation of Speech Using L1-Norm Sparse LP

    舟木　慶一

    Proc.ISPACS-2018     2018.11

    Type of publication: Research paper (scientific journal)

display all >>

To the head of this page.▲

Books 【 display / non-display 】

  • Low Computational Robust F0 Estimation of Speech Based on TV-CAR Analysis

    Keiichi Funaki and Takehito Higa ( Part: Multiple Authorship )

    INTEC-BOOK  2013.01

  • Speech Enhancement based on Iterative Wiener Filter using Complex LPC Speech Analysis

    Keiichi Funaki ( Part: Single Author )

    INTEC-BOOK  2009

To the head of this page.▲

Other Papers 【 display / non-display 】

display all >>

To the head of this page.▲

Presentations 【 display / non-display 】

  • On a robust ASR based on robust complex speech analysis

    Keita Higa and Keiichi Funaki

    ISPACS-2015(Bali,Indonesia)  2015.11  -  2015.11 

  • WLP-BASED TV-CAR SPEECH ANALYSIS AND ITS EVALUATION FOR F0 ESTIMATION

    Keiichi Funaki,Keita Higa

    MAVEBA-2013(Firenze, Italy)  2013.12  -  2013.12 

  • Low Computational robust F0 estimation based on time-varying complex speech analysis

    Keiichi Funaki and Takehito Higa

    SISA2011(Nagasaki,Japan)  2011.10  -  2011.10 

  • Speech Enhancement based on Iterative Wiener Filter using Robust Time-Varying Complex Speech Analysis," Proc.SISA2011

    Keiichi Funaki and Yusuke Inafuku

    SISA2011(Nagasaki,Japan)  2011.10  -  2011.10 

  • F0 Contour Estimation using ELS-based Robust Time-Varying Complex Speech Analysis

    Keiichi Funaki

    DSP/SPE workshop,（Sedona、AZ. USA）  2011.01  -  2011.01 

display all >>

To the head of this page.▲