Symbol graph based discriminative training and rescoring for improved math symbol recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2008, Pages 1953-1956

  Luo, Zhen Xuan ^a,b   Shi, Yu ^a   Soong, Frank K ^a  

^a MICROSOFT RESEARCH ASIA   (China)

^b SHANGHAI JIAO TONG UNIVERSITY   (China)

Author keywords

Discriminative training; Graph rescoring; Handwritten math formula recognition; Symbol graph; Symbol recognition

Indexed keywords

ACOUSTICS; FEATURE EXTRACTION; INTEGRATED OPTICS; MATHEMATICAL PROGRAMMING; SIGNAL PROCESSING; SPEECH; STEREOPHONIC BROADCASTING; SYSTEMS ENGINEERING;

DISCRIMINATIVE TRAINING; GRAPH RESCORING; HANDWRITTEN MATH FORMULA RECOGNITION; SYMBOL GRAPH; SYMBOL RECOGNITION;

CODES (SYMBOLS);

EID: 51449115620     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2008.4518019     Document Type: Conference Paper

References (4)

1. Y Shi, H. Y. Li, and F. K. Soong, "A unified framework for symbol segmentation and recognition of handwritten mathematical expressions," in ICDAR2007, 2007, vol. II, pp. 854-858.
2. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D thesis, July 2004.
3. R. Schluter and W. Macherey, "Comparison of discriminative training criteria," in ICASSP 1998, 1998, pp. 493-496.
4. S. Young et al, "The htk book (for htk version 3.3)," 2005.