메뉴 건너뛰기




Volumn , Issue , 2013, Pages 8091-8095

Weak top-down constraints for unsupervised acoustic model training

Author keywords

speaker independent acoustic models; spectral clustering; top down constraints; unsupervised training

Indexed keywords

ACOUSTIC MODEL; ACOUSTIC MODEL TRAININGS; DISCOVERY SYSTEMS; ISOLATED WORDS; PRONUNCIATION DICTIONARIES; SPECTRAL CLUSTERING; TOPDOWN; UNSUPERVISED TRAINING;

EID: 84890467020     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2013.6639241     Document Type: Conference Paper
Times cited : (61)

References (24)
  • 1
    • 64849085294 scopus 로고    scopus 로고
    • Unsupervised pattern discovery in speech
    • A. Park and J. R. Glass, "Unsupervised pattern discovery in speech," IEEE T-ASLP, vol. 16, no. 1, pp. 186-197, 2008.
    • (2008) IEEE T-ASLP , vol.16 , Issue.1 , pp. 186-197
    • Park, A.1    Glass, J.R.2
  • 2
    • 56149105470 scopus 로고    scopus 로고
    • A computational model for unsupervised word discovery
    • L. ten Bosch and B. Cranen, "A computational model for unsupervised word discovery," in Interspeech, 2007.
    • (2007) Interspeech
    • Ten Bosch, L.1    Cranen, B.2
  • 3
    • 70450214484 scopus 로고    scopus 로고
    • Audio keyword extraction by unsupervised word discovery
    • A. Muscariello, G. Gravier, and F. Bimbot, "Audio keyword extraction by unsupervised word discovery," in Interspeech, 2009.
    • (2009) Interspeech
    • Muscariello, A.1    Gravier, G.2    Bimbot, F.3
  • 4
    • 78049362755 scopus 로고    scopus 로고
    • Towards multi-speaker unsupervised speech pattern discovery
    • Y. Zhang and J. R. Glass, "Towards multi-speaker unsupervised speech pattern discovery," in Proc. of ICASSP, 2010.
    • (2010) Proc. of ICASSP
    • Zhang, Y.1    Glass, J.R.2
  • 5
    • 79959851706 scopus 로고    scopus 로고
    • Towards spoken term discovery at scale with zero resources
    • A. Jansen, K. Church, and H. Hermansky, "Towards spoken term discovery at scale with zero resources," in Interspeech, 2010.
    • (2010) Interspeech
    • Jansen, A.1    Church, K.2    Hermansky, H.3
  • 6
    • 84858987768 scopus 로고    scopus 로고
    • Efficient spoken term discovery using randomized algorithms
    • A. Jansen and B. Van Durme, "Efficient spoken term discovery using randomized algorithms," in Proc. ASRU, 2011.
    • (2011) Proc. ASRU
    • Jansen, A.1    Van Durme, B.2
  • 7
    • 77949473673 scopus 로고    scopus 로고
    • Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams
    • Y. Zhang and J. Glass, "Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams," in ASRU, 2009.
    • (2009) ASRU
    • Zhang, Y.1    Glass, J.2
  • 8
    • 84878566254 scopus 로고    scopus 로고
    • Indexing raw acoustic features for scalable zero resource search
    • A. Jansen and B. Van Durme, "Indexing raw acoustic features for scalable zero resource search," in Proc. Interspeech, 2012.
    • (2012) Proc. Interspeech
    • Jansen, A.1    Van Durme, B.2
  • 12
    • 70349210894 scopus 로고    scopus 로고
    • Unsupervised acoustic and language model training with small amounts of labeled data
    • S. Novotney, R. Schwartz, and J. Ma, "Unsupervised acoustic and language model training with small amounts of labeled data," in Proc. of ICASSP, 2009.
    • (2009) Proc. of ICASSP
    • Novotney, S.1    Schwartz, R.2    Ma, J.3
  • 14
    • 84865747527 scopus 로고    scopus 로고
    • Unsupervised audio patterns discovery using HMM-based self-organized units
    • M.-H. Siu, H. Gish, S. Lowe, and A. Chan, "Unsupervised audio patterns discovery using HMM-based self-organized units," in Proc. of Interspeech, 2011.
    • (2011) Proc. of Interspeech
    • Siu, M.-H.1    Gish, H.2    Lowe, S.3    Chan, A.4
  • 15
    • 84867602188 scopus 로고    scopus 로고
    • Speaker independent discriminant feature extraction for acoustic pattern matching
    • X. Anguera, "Speaker independent discriminant feature extraction for acoustic pattern matching," in Proc. ICASSP, 2012.
    • (2012) Proc. ICASSP
    • Anguera, X.1
  • 16
    • 84867809023 scopus 로고    scopus 로고
    • A nonparametric Bayesian approach to acoustic model discovery
    • C.-Y. Lee and J. Glass, "A nonparametric Bayesian approach to acoustic model discovery," in Proc. ACL, 2012.
    • (2012) Proc. ACL
    • Lee, C.-Y.1    Glass, J.2
  • 17
    • 84865770260 scopus 로고    scopus 로고
    • Towards unsupervised training of speaker independent acoustic models
    • A. Jansen and K. Church, "Towards unsupervised training of speaker independent acoustic models," in Interspeech, 2011.
    • (2011) Interspeech
    • Jansen, A.1    Church, K.2
  • 19
    • 0017930815 scopus 로고
    • Dynamic programming algorithm optimization for spoken word recognition
    • H. Sakoe and S. Chiba, "Dynamic programming algorithm optimization for spoken word recognition," IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. ASSP-26, no. 1, pp. 43-49, 1978.
    • (1978) IEEE Transactions on Acoustics, Speech, and Signal Processing , vol.ASSP-26 , Issue.1 , pp. 43-49
    • Sakoe, H.1    Chiba, S.2
  • 21
    • 0025041264 scopus 로고
    • Perceptual linear predictive (PLP) analysis of speech
    • H. Hermansky, "Perceptual linear predictive (PLP) analysis of speech," Journal of the Acoustical Society of America, vol. 87, no. 4, pp. 1738-1752, 1990.
    • (1990) Journal of the Acoustical Society of America , vol.87 , Issue.4 , pp. 1738-1752
    • Hermansky, H.1
  • 23
    • 84858969928 scopus 로고    scopus 로고
    • Rapid evaluation of speech representations for spoken term discovery
    • M. Carlin, S. Thomas, A. Jansen, and H. Hermansky, "Rapid evaluation of speech representations for spoken term discovery," in Proc. of ICASSP, 2011.
    • (2011) Proc. of ICASSP
    • Carlin, M.1    Thomas, S.2    Jansen, A.3    Hermansky, H.4
  • 24
    • 84878421054 scopus 로고    scopus 로고
    • Intrinsic spectral analysis for zero and high resource speech recognition
    • A. Jansen, S. Thomas, and H. Hermansky, "Intrinsic spectral analysis for zero and high resource speech recognition," in Proc. of Interspeech, 2012.
    • (2012) Proc. of Interspeech
    • Jansen, A.1    Thomas, S.2    Hermansky, H.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.