Discriminative Optimization of the Figure of Merit for Phonetic Spoken Term Detection
- 3 December 2010
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 19 (6) , 1677-1687
Abstract
This paper proposes to improve spoken term detection (STD) accuracy by optimizing the figure of merit (FOM). In this paper, the index takes the form of a phonetic posterior-feature matrix. Accuracy is improved by formulating STD as a discriminative training problem and directly optimizing the FOM, through its use as an objective function to train a transformation of the index. The outcome of indexing is then a matrix of enhanced posterior-features that are directly tailored for the STD task. The technique is shown to improve the FOM by up to 13% on held-out data. Additional analysis explores the effect of the technique on phone recognition accuracy, examines the actual values of the learned transform, and demonstrates that using an extended training data set results in further improvement in the FOM.Keywords
This publication has 16 references indexed in Scilit:
- Spoken term detection using fast phonetic decoding2009
- Discriminative Keyword Spotting2009
- Hierarchical integration of phonetic and lexical knowledge in phone posterior estimationInternational Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2008
- Indexing and Search Methods for Spoken DocumentsLecture Notes in Computer Science, 2006
- Vocabulary-independent indexing of spontaneous speechIEEE Transactions on Speech and Audio Processing, 2005
- Learning to rank using gradient descent2005
- Phoneme Based Acoustics Keyword Spotting in Informal Continuous Speech2005
- A MFoM learning approach to robust multiclass multi-label text categorization2004
- A multistage algorithm for spotting new words in speechIEEE Transactions on Speech and Audio Processing, 2002
- Numerical Optimization1999