Automatic Question Generation for HMM State Tying using a Feature Table

Aqueous, alkaline, liquid solutions consisting essentially of NaMnO4 and NaOH provide high etch rates for, e.g., printed circuit boards. The solutions can be used to desmear and etchback, and produce manganese residues on the surface of the board which are readily removed by acid neutralization alone.

[1]  Julie Carson-Berndsen,et al.  Multi-linear HMM based system for articulatory feature extraction , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

[2]  Jj Odell,et al.  The Use of Context in Large Vocabulary Speech Recognition , 1995 .

[3]  Supphanat Kanokphara.  Syllable structure based phonetic units for context-dependent continuous Thai speech recognition , 2003, INTERSPEECH.

[4]  Julie Carson-Berndsen,et al.  HARTFEX: a multi-dimentional system of HMM based recognisers for articulatory features extraction , 2003, NOLISP.

[5]  Richard M. Stern,et al.  Automatic clustering and generation of contextual questions for tied states in hidden Markov models , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[6]  Alexis Bernard,et al.  Automatic and language independent triphone training using phonetic tables [speech recognition] , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.