• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to previous page

Classification of Japanese Consonants in terms of Structured Modeling and Geometrical Interpretation of Dynamic Characteristics in Transient Parts

Research Project

Project/Area Number 02805044
Research Category

Grant-in-Aid for General Scientific Research (C)

Allocation TypeSingle-year Grants
Research Field 情報工学
Research InstitutionNiigata University

Principal Investigator

HORI Jun-ichi  Faculty of Engineering, Niigata University, Research Associate, 工学部, 助手 (80209262)

Co-Investigator(Kenkyū-buntansha) OHKUBO Masaki  College of Biomedical Technology, Niigata University, Research Associate, 医療技術短期大学部, 助手 (10203738)
KIRYU Tohru  Faculty of Engineering, Niigata University, Assistant Professor, 工学部, 助教授 (80115021)
Project Period (FY) 1990 – 1991
Project Status Completed (Fiscal Year 1991)
Budget Amount *help
¥1,900,000 (Direct Cost: ¥1,900,000)
Fiscal Year 1991: ¥500,000 (Direct Cost: ¥500,000)
Fiscal Year 1990: ¥1,400,000 (Direct Cost: ¥1,400,000)
Keywordstransient part / dynamic characteristics / natural observation filter / consonants / reconstruction / fricatives / stops / trajectory / 後続母音 / 自然観測法 / 連鎖母音 / 調音結合区間 / 時係列 / 射影 / 個別差 / 後続母音予測
Research Abstract

Transient part of speech signals has been of great interest these years in speech recognition. Furui proposed delta cepstrum coefficients to extract a dynamic characteristic of speech signals and achieved higher recognition rate than ever [1986]. It should be noted, however, that conventional approaches including the dynamic characteristics depend on a linear prediction that features formats of speech signals. We employed a structural model named the natural observation system for speech modeling and a geometrical interpretation to classify the types of transient parts.
A natural observation filter (NOF) consists of a series of first order filters with the same cutoff frequency : a low pass filter of a first stage followed by high pass filters. The NOF can reconstruct an input signal with a linear combination of outputs at each stage of first order filters, employing appropriate coefficients. We called them natural observation coefficients (NOCs). We can analyze signals by the time courses of NOCs with multi-cutoff frequencies (NOC pattern), because each NOC is a function of the cutoff frequency. We applied the NOC pattern for Japanese consonants, fricatives and stops, to study the transient parts of speech signals. Consequently, we obtained distinguishable NOC patterns that probably reflect an instantaneous structure of Japanese consonants, fricatives and stops, and following vowels.
On the other hand, we used a geometrical interpretation of the transient parts. A two-dimensional plane in the p-dimensional Hilbert space was determined so that the trajectory of coefficients vector becomes as straight as possible. We use three types of parameters, including linear prediction coefficients, LPC cepstrum coefficients, and NOCs which are structured parameters. As a result, NOCs show a rather straight line than the other two. Limiting to LPC cepstrum coefficients, the smoothly progressive trajectory to a following vowel contributed to the high recognition rate.

Report

(3 results)
  • 1991 Annual Research Report   Final Research Report Summary
  • 1990 Annual Research Report
  • Research Products

    (3 results)

All Other

All Publications (3 results)

  • [Publications] 木竜 徹,野田 泰之,堀 潤一,齊藤 義明: "自然観測係数パタ-ンによる摩擦音・破裂音での遷移区間の解析" 電子情報通信学会技術速報. SP. (1992)

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      1991 Final Research Report Summary
  • [Publications] Tohru Kiryu, Yasuyuki Noda, Jun-ichi Hori and Yoshiaki Saitoh: "Analysis of transit part of Japanese consonants by a natural observation coefficients with multi-cutoff frequencies." IEICE Technical Report. SP. (1992)

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      1991 Final Research Report Summary
  • [Publications] 木竜 徹: "自然観測係数パタ-ンによる摩擦音・破裂音での遷移区間の解析" 電子情報学会技術速報. SP. (1992)

    • Related Report
      1991 Annual Research Report

URL: 

Published: 1990-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi