Improving acoustic models with captioned multimedia speech

International Conference on Multimedia Computing and Systems -Proceedings

Volumn 2, Issue , 1999, Pages 767-771

  Jang, Photina Jaeyun ^a   Hauptmann, Alexander G ^a  

^a CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ERRORS; MARKOV PROCESSES; MULTIMEDIA SYSTEMS; NEURAL NETWORKS; SPEECH CODING;

HIDDEN MARKOV MODEL; WORD ERROR RATE;

CONTINUOUS SPEECH RECOGNITION;

EID: 0032659923     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Article

References (8)