Fast HMM-Filler Approach for Key Word Spotting in Handwritten Documents
Authors:
- Alejandro Hector ToselliATAlejandro Hector Toselli
- Enrique VidalEVEnrique Vidal
- 1 August 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 5 (15205363) , 501-505
Abstract
The so-called filler or garbage Hidden Markov Models (HMM) are among the most widely used models for lexicon-free, query by string key word spotting in the fields of speech recognition and (lately) handwritten text recognition. An important drawback of this approach is the large computational cost of the keyword-specific HMM Viterbi decoding process needed to obtain the confidence scores of each word to be spotted. This paper presents a novel way to compute such confidence scores, directly from character lattices produced during a single Viterbi decoding process using only the "filler" model (i.e. no explicit keyword-specific decoding is needed). Experiments show that, as compared with the classical HMM-filler approach, the proposed method obtains essentially the same spotting results, while requiring between one and two orders of magnitude less query computing time.Keywords
This publication has 8 references indexed in Scilit:
- Script Independent Word Spotting in Offline Handwritten Documents Based on Hidden Markov Models2012
- Lexicon-free handwritten word spotting using character HMMsPattern Recognition Letters, 2012
- A Novel Word Spotting Method Based on Recurrent Neural NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Discriminative keyword spottingSpeech Communication, 2009
- A new interpretation of average precision2008
- Introduction to Information Retrieval2008
- The IAM-database: an English sentence database for offline handwriting recognitionInternational Journal on Document Analysis and Recognition (IJDAR), 2002
- Confidence measures for large vocabulary continuous speech recognitionIEEE Transactions on Speech and Audio Processing, 2001