An efficient multistage ROVER method for automatic speech recognition

Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009

Volumn , Issue , 2009, Pages 894-897

  Haihua, Xu ^a   Jie, Zhu ^a   Guanyong, Wu ^a  

^a SHANGHAI JIAO TONG UNIVERSITY   (China)

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;

FEATURE EXTRACTION; MAXIMUM LIKELIHOOD ESTIMATION; MULTIMEDIA SYSTEMS; REMELTING; STEREOPHONIC BROADCASTING;

SPEECH RECOGNITION;

EID: 70449581251     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICME.2009.5202639     Document Type: Conference Paper

References (11)

1. 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.
2. H.Schwenk and J.L. Gauvain, "Combining Multiple Speech Recognizers using Voting and Language Model Information," in ICSLP, 2000.
3. O.Siohan, B.Ramabhadran, and B.Kingsbury, "Constructing Ensembels of ASR Systems using Randomized Decision Trees," in ICASSP, 2005.
4. C.Breslin and M.J.F.Gales, "Generating Complementary Systems for Speech Recognition," in ICSLP, 2006.
5. G.Evermann and P.C.Woodland, "Posterior Probability Decoding, Confidence Estimation and System Combination," in Proc.of the NIST Speech Transcription Workshop, 2000.
6. D.Povey, D.Kanevsky, B.Kingsbury, and et al, "Boosted MMI for Model and Feature-space Discriminative Training," in ICASSP, 2008.
7. C.J.Leggetter and P.C.Woodland, "Speaker Adaptation of Continuous Density HMMs using Multivariate Linear Regression," in ICSLP, 1994.
8. Povey D., Discriminative Training for Large Vocabulary Speech Recognition, Ph.D.thesis, Cambridge University, 2004.
9. Fei Sha and Lawrence K.Saul, "Large Margin Gaussian Mixture Modeling for Phonetic Classification and Recognition," in ICASSP, 2006.
10. 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.
11. X. Haihua and Z.Jie, "Towards More Efficient and Accurate Methods for Mandarin LVCSR Discriminative Training," in ICME, 2008.