메뉴 건너뛰기




Volumn 4, Issue , 2006, Pages 1598-1601

Local transformation models for speech recognition

Author keywords

Local frequency warping; Speaker variability

Indexed keywords

DEGREES OF FREEDOM (MECHANICS); ERRORS; HIDDEN MARKOV MODELS; LOUDSPEAKERS; MARKOV PROCESSES;

EID: 44949166839     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (5)

References (8)
  • 1
    • 0031647824 scopus 로고    scopus 로고
    • A frequency warping approach to speaker normalization
    • L. Lee and R. Rose, "A frequency warping approach to speaker normalization," IEEE Trans. on SAP, vol. 1, no. 6, pp. 49-60, 1998.
    • (1998) IEEE Trans. on SAP , vol.1 , Issue.6 , pp. 49-60
    • Lee, L.1    Rose, R.2
  • 2
    • 85009063791 scopus 로고    scopus 로고
    • Using VTLN for broadcast news transcription
    • Jeju Island, S.Korea, October
    • D. Kim, S. Umesh, M. J. Gales, T Hain, and P. Woodland, "Using VTLN for broadcast news transcription," in Proc. IC-SLP, Jeju Island, S.Korea, October 2004.
    • (2004) Proc. IC-SLP
    • Kim, D.1    Umesh, S.2    Gales, M.J.3    Hain, T.4    Woodland, P.5
  • 3
    • 0029288633 scopus 로고
    • Maximum likelihood linear regression for speaker adaptation of the parameters of continuous density hidden markov models
    • C. J. Legetter and P. C. Woodland, "Maximum likelihood linear regression for speaker adaptation of the parameters of continuous density hidden markov models," Computer Speech and Language, vol. 9, pp. 171-185, 1995.
    • (1995) Computer Speech and Language , vol.9 , pp. 171-185
    • Legetter, C.J.1    Woodland, P.C.2
  • 4
    • 0031624341 scopus 로고    scopus 로고
    • Speaker normalized acoustic modeling based on 3-D viterbi decoding
    • Seattle, USA
    • T. Fukada and Y. Sagisaka, "Speaker normalized acoustic modeling based on 3-D viterbi decoding," in Proc. ICASSP, Seattle, USA, 1998, vol. 1, pp. 437-440.
    • (1998) Proc. ICASSP , vol.1 , pp. 437-440
    • Fukada, T.1    Sagisaka, Y.2
  • 5
    • 33745208423 scopus 로고    scopus 로고
    • Augmented state space acoustic decoding for modeling local variability in speech
    • Lisbon, Portugal
    • A. Miguel, E. Lleida, R. Rose, L. Buera, and A. Ortega, "Augmented state space acoustic decoding for modeling local variability in speech," in Proc. Eurospeech, Lisbon, Portugal, 2005, pp. 3009-3012.
    • (2005) Proc. Eurospeech , pp. 3009-3012
    • Miguel, A.1    Lleida, E.2    Rose, R.3    Buera, L.4    Ortega, A.5
  • 6
    • 33947626630 scopus 로고    scopus 로고
    • On the interaction between speaker normalization, environment compensation, and discriminant feature space transformations
    • Toulouse, France, May
    • R. Rose, A. Keyvani, and A. Miguel, "On the interaction between speaker normalization, environment compensation, and discriminant feature space transformations," in Proc. ICASSP, Toulouse, France, May 2006.
    • (2006) Proc. ICASSP
    • Rose, R.1    Keyvani, A.2    Miguel, A.3
  • 7
    • 27644522706 scopus 로고    scopus 로고
    • Vocal tract normalization equals linear transformation in cepstral space
    • September
    • M. Pitz and H. Ney, "Vocal tract normalization equals linear transformation in cepstral space," IEEE Trans. on SAP, vol. 13, no. 5, pp. 930-944, September 2005.
    • (2005) IEEE Trans. on SAP , vol.13 , Issue.5 , pp. 930-944
    • Pitz, M.1    Ney, H.2
  • 8
    • 10044224253 scopus 로고    scopus 로고
    • Bernoulli mixture models for binary images
    • Cambridge, UK, August
    • A. Juan and E. Vidal, "Bernoulli mixture models for binary images," in Proc. ICPR, Cambridge, UK, August 2004, vol. 2.
    • (2004) Proc. ICPR , vol.2
    • Juan, A.1    Vidal, E.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.