메뉴 건너뛰기




Volumn , Issue , 2009, Pages 894-897

An efficient multistage ROVER method for automatic speech recognition

Author keywords

ASR; ROVER; Unsupervised model adaptation

Indexed keywords

ASR; AUTOMATIC SPEECH RECOGNITION; DECODING METHODS; MAXIMUM A POSTERIORI; MAXIMUM LIKELIHOOD LINEAR REGRESSION; MAXIMUM MUTUAL INFORMATION; MINIMUM PHONE ERROR; RECOGNITION ACCURACY; RECOGNIZER OUTPUT VOTING ERROR REDUCTIONS; ROVER; SINGLE STAGE; UNSUPERVISED MODEL ADAPTATION; WORD ERROR RATE;

EID: 70449581251     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICME.2009.5202639     Document Type: Conference Paper
Times cited : (10)

References (11)
  • 1
    • 0030638031 scopus 로고    scopus 로고
    • A Post-processing System to Yield Reduced Word Error Rates:Recongiser Output Voting Error Reduction(ROVER)
    • J.G.Fiscus, "A Post-processing System to Yield Reduced Word Error Rates:Recongiser Output Voting Error Reduction(ROVER)," in Proc.IEEE ASRU Workshop, 1997.
    • (1997) Proc.IEEE ASRU Workshop
    • Fiscus, J.G.1
  • 2
    • 84922926713 scopus 로고    scopus 로고
    • Combining Multiple Speech Recognizers using Voting and Language Model Information
    • H.Schwenk and J.L. Gauvain, "Combining Multiple Speech Recognizers using Voting and Language Model Information," in ICSLP, 2000.
    • (2000) ICSLP
    • Schwenk, H.1    Gauvain, J.L.2
  • 3
    • 33646818291 scopus 로고    scopus 로고
    • Constructing Ensembels of ASR Systems using Randomized Decision Trees
    • O.Siohan, B.Ramabhadran, and B.Kingsbury, "Constructing Ensembels of ASR Systems using Randomized Decision Trees," in ICASSP, 2005.
    • (2005) ICASSP
    • Siohan, O.1    Ramabhadran, B.2    Kingsbury, B.3
  • 4
    • 34547497829 scopus 로고    scopus 로고
    • Generating Complementary Systems for Speech Recognition
    • C.Breslin and M.J.F.Gales, "Generating Complementary Systems for Speech Recognition," in ICSLP, 2006.
    • (2006) ICSLP
    • Breslin, C.1    Gales, M.J.F.2
  • 6
    • 51449120120 scopus 로고    scopus 로고
    • Boosted MMI for Model and Feature-space Discriminative Training
    • D.Povey, D.Kanevsky, B.Kingsbury, and et al, "Boosted MMI for Model and Feature-space Discriminative Training," in ICASSP, 2008.
    • (2008) ICASSP
    • Povey, D.1    Kanevsky, D.2    Kingsbury, B.3    and et, al.4
  • 7
    • 84864010278 scopus 로고
    • Speaker Adaptation of Continuous Density HMMs using Multivariate Linear Regression
    • C.J.Leggetter and P.C.Woodland, "Speaker Adaptation of Continuous Density HMMs using Multivariate Linear Regression," in ICSLP, 1994.
    • (1994) ICSLP
    • Leggetter, C.J.1    Woodland, P.C.2
  • 9
    • 33947686745 scopus 로고    scopus 로고
    • Large Margin Gaussian Mixture Modeling for Phonetic Classification and Recognition
    • Fei Sha and Lawrence K.Saul, "Large Margin Gaussian Mixture Modeling for Phonetic Classification and Recognition," in ICASSP, 2006.
    • (2006) ICASSP
    • Sha, F.1    Saul, L.K.2
  • 10
    • 34547522370 scopus 로고    scopus 로고
    • Comparison of Large Margin Training to other Discriminative Methods for Phonetic Recognition by Hidden Markov Models
    • Fei Sha and Lawrence K.Saul, "Comparison of Large Margin Training to other Discriminative Methods for Phonetic Recognition by Hidden Markov Models," in ICASSP, 2007.
    • (2007) ICASSP
    • Sha, F.1    Saul, L.K.2
  • 11
    • 70449584636 scopus 로고    scopus 로고
    • Towards More Efficient and Accurate Methods for Mandarin LVCSR Discriminative Training
    • X. Haihua and Z.Jie, "Towards More Efficient and Accurate Methods for Mandarin LVCSR Discriminative Training," in ICME, 2008.
    • (2008) ICME
    • Haihua, X.1    Jie, Z.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.