메뉴 건너뛰기




Volumn , Issue , 2007, Pages 348-351

Investigating data selection for minimum phone error training of acoustic models

Author keywords

[No Author keywords available]

Indexed keywords

DATA REDUCTION;

EID: 46449108334     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/icme.2007.4284658     Document Type: Conference Paper
Times cited : (14)

References (12)
  • 1
    • 0036296863 scopus 로고    scopus 로고
    • Minimum Phone Error, and I-Smoothing for Improved Discriminative Training
    • D. Pcvey, P.C. Woodland, "Minimum Phone Error, and I-Smoothing for Improved Discriminative Training," in Proc. ICASSP 2002.
    • Proc. ICASSP 2002
    • Pcvey, D.1    Woodland, P.C.2
  • 2
    • 46449138280 scopus 로고    scopus 로고
    • An Empirical Study of Word Error Minimization Approaches for Mandarin Large Vocabulary Speech Recognition
    • JW. Kuo et al, "An Empirical Study of Word Error Minimization Approaches for Mandarin Large Vocabulary Speech Recognition," IJCLCLP, Vol. 11(3), 2006.
    • (2006) IJCLCLP , vol.11 , Issue.3
    • Kuo, J.W.1
  • 3
    • 0024889270 scopus 로고    scopus 로고
    • A Generalization of the Baum Algorithm to Rational Objective Functions
    • P. S. Gopalakrishnan et al., "A Generalization of the Baum Algorithm to Rational Objective Functions," in Proc. ICASSP 1989.
    • Proc. ICASSP 1989
    • Gopalakrishnan, P.S.1
  • 4
    • 46449123880 scopus 로고    scopus 로고
    • Spectral Entropy Feature in Full-Combination Multi-Stream for Robust ASR
    • H. Misra, H. Bourlard, "Spectral Entropy Feature in Full-Combination Multi-Stream for Robust ASR," in Proc. Eurospeech 2005.
    • Proc. Eurospeech 2005
    • Misra, H.1    Bourlard, H.2
  • 5
    • 34047115134 scopus 로고    scopus 로고
    • Large Margin Hidden Markov Models for Speech Recognition
    • H. Jiang et al., "Large Margin Hidden Markov Models for Speech Recognition," IEEE Trans. ASLP 14(5), 2006.
    • (2006) IEEE Trans. ASLP , vol.14 , Issue.5
    • Jiang, H.1
  • 6
    • 46449089938 scopus 로고    scopus 로고
    • The Use of Frame-level Information Cues for Minimum Phone Error Discriminative Training of Acoustic Models
    • S.H. Liu and Berlin Chen, "The Use of Frame-level Information Cues for Minimum Phone Error Discriminative Training of Acoustic Models," in Proc. TAAI 2006.
    • Proc. TAAI 2006
    • Liu, S.H.1    Chen, B.2
  • 7
    • 34547499036 scopus 로고    scopus 로고
    • Improved Discriminative Training using Phone Lattices
    • J. Zheng, A. Stoicke, "Improved Discriminative Training using Phone Lattices," in Proc. Eurospeech 2005
    • (2005) Proc. Eurospeech
    • Zheng, J.1    Stoicke, A.2
  • 8
    • 0034856258 scopus 로고    scopus 로고
    • Explicit Word Error Minimization Using Word Hypothesis Posterior Probability
    • F. Wessel et al., "Explicit Word Error Minimization Using Word Hypothesis Posterior Probability," in Proc. ICASSP 2001.
    • Proc. ICASSP 2001
    • Wessel, F.1
  • 9
    • 33846220725 scopus 로고    scopus 로고
    • Minimum Exact Word Error Training
    • G. Heigold et al., "Minimum Exact Word Error Training," in Proc. ASRU 2005.
    • Proc. ASRU 2005
    • Heigold, G.1
  • 10
    • 60849127172 scopus 로고    scopus 로고
    • Lightly Supervised and Data-Driven Approaches to Mandarin Broadcast News Transcription
    • B. Chen et al., "Lightly Supervised and Data-Driven Approaches to Mandarin Broadcast News Transcription," in Proc. ICASSP 2004.
    • Proc. ICASSP 2004
    • Chen, B.1
  • 11
    • 34547505668 scopus 로고    scopus 로고
    • Word Topical Mixture Models for Dynamic Language Model Adaptation
    • H.S. Chiu and B. Chen, "Word Topical Mixture Models for Dynamic Language Model Adaptation," in Proc. ICASSP 2007.
    • Proc. ICASSP 2007
    • Chiu, H.S.1    Chen, B.2
  • 12
    • 0024909979 scopus 로고    scopus 로고
    • Some Statistical Issues in the Comparison of Speech Recognition Algorithms
    • L. Gillick and S. Cox, "Some Statistical Issues in the Comparison of Speech Recognition Algorithms," in Proc. ICASSP 1989.
    • Proc. ICASSP 1989
    • Gillick, L.1    Cox, S.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.