RISS 학술연구정보서비스

검색
다국어 입력

http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

변환된 중국어를 복사하여 사용하시면 됩니다.

예시)
  • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
  • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
닫기
    인기검색어 순위 펼치기

    RISS 인기검색어

      Data-Driven Attribute Set Generation for Decision Tree-based Clustering

      한글로보기

      https://www.riss.kr/link?id=T10085177

      • 0

        상세조회
      • 0

        다운로드
      서지정보 열기
      • 내보내기
      • 내책장담기
      • 공유하기
      • 오류접수

      부가정보

      다국어 초록 (Multilingual Abstract)

      In automatic speech recognition, decision trees are widely used in an unsupervised fashion to cluster and classify the states of HMMs (hidden Markov models). Decision tree-based clustering uses prior knowledge of a language for its attribute set, which is called a phonetic attribute set or question set. The phonetic attribute set, which contains questions about the context of current speech sound, is usually provided by linguistic or phonetic experts. The knowledge-based phonetic attribute set, however, has some drawbacks in terms of its quality and may degrade the homogeneity of the cluster generated based on it. Also, it is inconvenient because we have to get help from human experts every time the language of the PLU (phone-like unit) of a recognition system is changed. In this thesis, therefore, problems of the knowledge-based attribute set are analyzed and a novel approach to producing a data-driven phonetic attribute set is proposed. Since the proposed method generates the attributes using backed-off HMMs, it may enhance the quality of the attributes and remove the inconvenience associated with the manual labor involved. In large vocabulary speech recognition experiments, it was found the proposed algorithms reduce the error rate by 4.0% for the TIMIT English corpus and 14.3% for the Korean corpus.
      번역하기

      In automatic speech recognition, decision trees are widely used in an unsupervised fashion to cluster and classify the states of HMMs (hidden Markov models). Decision tree-based clustering uses prior knowledge of a language for its attribute set, whic...

      In automatic speech recognition, decision trees are widely used in an unsupervised fashion to cluster and classify the states of HMMs (hidden Markov models). Decision tree-based clustering uses prior knowledge of a language for its attribute set, which is called a phonetic attribute set or question set. The phonetic attribute set, which contains questions about the context of current speech sound, is usually provided by linguistic or phonetic experts. The knowledge-based phonetic attribute set, however, has some drawbacks in terms of its quality and may degrade the homogeneity of the cluster generated based on it. Also, it is inconvenient because we have to get help from human experts every time the language of the PLU (phone-like unit) of a recognition system is changed. In this thesis, therefore, problems of the knowledge-based attribute set are analyzed and a novel approach to producing a data-driven phonetic attribute set is proposed. Since the proposed method generates the attributes using backed-off HMMs, it may enhance the quality of the attributes and remove the inconvenience associated with the manual labor involved. In large vocabulary speech recognition experiments, it was found the proposed algorithms reduce the error rate by 4.0% for the TIMIT English corpus and 14.3% for the Korean corpus.

      더보기

      목차 (Table of Contents)

      • Abstract = ⅰ
      • Contents = ⅱ
      • Chapter 1 Introduction = 1
      • Chapter 2 State Clustering in HMM-based Speech Recognition = 4
      • 2.1 Purposes and Brief Description = 4
      • Abstract = ⅰ
      • Contents = ⅱ
      • Chapter 1 Introduction = 1
      • Chapter 2 State Clustering in HMM-based Speech Recognition = 4
      • 2.1 Purposes and Brief Description = 4
      • 2.2 Bottom-Up vs. Decision Tree-based Clustering = 6
      • Chapter 3 Analysis of Phonetic Attribute Sets = 9
      • 3.1 Knowledge-based English Attribute Set = 10
      • 3.2 Knowledge-based Korean Attribute Set = 13
      • 3.3 Data-driven Phonetic Attribute Set = 16
      • Chapter 4 Data-driven Phonetic Attribute Set Generation = 18
      • 4.1 Bhattacharyya Distance = 18
      • 4.2 Diphone-based Algorithm = 19
      • 4.3 Monophone-based Algorithm = 22
      • Chapter 5 Results of Experiments = 26
      • 5.1 Environment of Experiments = 27
      • 5.2 Knowledge-based vs. Data-driven Attribute Sets = 27
      • 5.3 Diphone-based vs. Monophone-based Algorithms = 31
      • 5.4 Language Independence = 33
      • Chapter 6 Conclusion = 36
      • References = 38
      더보기

      분석정보

      View

      상세정보조회

      0

      Usage

      원문다운로드

      0

      대출신청

      0

      복사신청

      0

      EDDS신청

      0

      동일 주제 내 활용도 TOP

      더보기

      주제

      연도별 연구동향

      연도별 활용동향

      연관논문

      연구자 네트워크맵

      공동연구자 (7)

      유사연구자 (20) 활용도상위20명

      이 자료와 함께 이용한 RISS 자료

      나만을 위한 추천자료

      해외이동버튼