Method and apparatus of hierarchically organizing an acoustic model for speech recognition and adaptation of the model to unseen domains
作者： Juergen Fritsch
DOI:
关键词:
摘要: A method of organizing an acoustic model for speech recognition is comprised the steps calculating a measure dissimilarity subphonetic units. clustering technique recursively applied to units based on calculated automatically generate hierarchically arranged model. Each application produces another level hierarchy with levels progressing from least specific most specific. adapting structure and size trained unseen domain using only small amount adaptation data also disclosed.
lens.org 参考文章(19)
Jürgen Fritsch, Michael Finke, Alex Waibel, Effective structural adaptation of LVCSR systems to unseen domains using hierarchical connectionist acoustic models. conference of the international speech communication association. ,(1998)
PC Woodland, CJ Leggetter, Speaker adaptation of HMMs using linear regression Cambridge University Engineering Department. ,(1994)
Anthony John Robinson, Recognition of sequential data using finite state sequence models organized in a tree structure ,(1998)
Mukund Panmanabhan, Stephane Herman Maes, Ramesh Ambat Gopinath, Lazaros Polymenakos, Lalit Rai Bahl, Ponani Gopalakrishnan, Transcription of speech data with segments from acoustically dissimilar environments ,(1997)
Alan K. Hunt, Thomas B. Schalk, Method for continuous recognition of alphanumeric strings spoken over a telephone network ,(1992)
Junichi Takami, Acoustic model generating method for speech recognition Journal of the Acoustical Society of America. ,vol. 105, pp. 2555- ,(1995) , 10.1121/1.426930
Laurence S Gillick, Francesco Scattone, Apparatuses and methods for developing and using models for speech recognition The Journal of the Acoustical Society of America. ,vol. 104, pp. 1900- ,(1998) , 10.1121/1.424201
Juergen Schuermann, Wolfgang Doster, A decision theoretic approach to hierarchical classifier design Pattern Recognition. ,vol. 17, pp. 359- 369 ,(1984) , 10.1016/0031-3203(84)90087-6
David M. Lubensky, Automated speech recognition using a plurality of different multilayer perception structures to model a plurality of distinct phoneme categories The Journal of the Acoustical Society of America. ,vol. 104, pp. 3157- ,(1998) , 10.1121/1.424259
George R. Doddington, Speech analysis method and apparatus The Journal of the Acoustical Society of America. ,vol. 97, pp. 3928- 3928 ,(1995) , 10.1121/1.413062