Probabilistic interpretation and improvements to the HMM-filler for handwritten keyword spotting
Authors:
- 1 August 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 731-735
Abstract
Traditionally, the HMM-Filler approach has been widely used in the fields of speech recognition and handwritten text recognition to tackle lexicon-free, query-by-string keyword spotting (KWS). It computes a score to determine whether a given keyword is written in a certain image region. It is conjectured, that this score is related to the confidence of the system, respect to the previous question. However, it is still not clear what this relationship is. In this paper, the HMM-Filler score is derived from a probabilistic formulation of KWS, which gives a better understanding of its behavior and limits. Additionally, the same probabilistic framework is used to present a new algorithm to compute the KWS scores, which results in better average precision (AP), for a keyword spotting task in the widely used IAM database. We show that the new algorithm can improve the HMM-filler results up to 10.4% relative (5.3% absolute) points in AP, in the considered task.Keywords
This publication has 10 references indexed in Scilit:
- Context-aware lattice based filler approach for key word spotting in handwritten documents2015
- Word-Graph and Character-Lattice Combination for KWS in Handwritten Documents2014
- Improving HMM-Based Keyword Spotting with Character Language Models2013
- Fast HMM-Filler Approach for Key Word Spotting in Handwritten Documents2013
- 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
- Introduction to Information Retrieval2008
- The IAM-database: an English sentence database for offline handwriting recognitionInternational Journal on Document Analysis and Recognition (IJDAR), 2002
- Fast Pattern Matching in StringsSIAM Journal on Computing, 1977