Discriminative optimisation of the figure of merit for phonetic spoken term detection
Data(s) |
2011
|
---|---|
Resumo |
This work proposes to improve spoken term detection (STD) accuracy by optimising the Figure of Merit (FOM). In this article, the index takes the form of phonetic posterior-feature matrix. Accuracy is improved by formulating STD as a discriminative training problem and directly optimising 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. |
Formato |
application/pdf |
Identificador | |
Publicador |
IEEE Signal Processing Society |
Relação |
http://eprints.qut.edu.au/40862/1/40862.pdf DOI:10.1109/TASL.2010.2096215 Wallace, R., Baker, B., Vogt, R., & Sridharan, S. (2011) Discriminative optimisation of the figure of merit for phonetic spoken term detection. IEEE Transactions on Audio, Speech, and Language Processing, 19(6), pp. 1677-1687. |
Direitos |
Copyright 2010 IEEE Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. |
Fonte |
Faculty of Built Environment and Engineering; Information Security Institute; School of Engineering Systems |
Palavras-Chave | #170204 Linguistic Processes (incl. Speech Production and Comprehension) #Spoken Term #Speech Processing #Speech Recognition #Information Retrieval |
Tipo |
Journal Article |