Toward island-of-reliability-driven very-large-vocabulary on-line handwriting recognition using character confidence scoring

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

Volumn 3, Issue , 2001, Pages 1525-1528

  Pitrelli, J F ^a   Subrahmonia, J ^a   Maison, B ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY; STATISTICAL METHODS;

HANDWRITING RECOGNITION; HIDDEN MARKOV MODELS;

CHARACTER RECOGNITION;

EID: 0034848664     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. Large vocabulary decoding and confidence estimation using word posterior probabilities
2. UNIPEN project of on-line data exchange and recognizer benchmarks
3. Estimating confidence using word lattices
4. Robust confidence annotation and rejection for continuous speech recognition
5. Finding consensus among words: Lattice-based word error minimization
6. Real-time on-line unconstrained handwriting recognition using statistical methods
7. Neural network-based context driven recognition of on-line cursive script
8. Quantifying the contribution of language modeling to writer-independent on-line handwriting recognition
9. Explicit word error minimization in N-best list rescoring
10. Writer dependent recognition of on-line unconstrained handwriting