Optimising figure of merit for phonetic spoken term detection
Contribuinte(s) |
Douglas, Scott |
---|---|
Data(s) |
2010
|
Resumo |
This paper introduces a novel technique to directly optimise the Figure of Merit (FOM) for phonetic spoken term detection. The FOM is a popular measure of sTD accuracy, making it an ideal candiate for use as an objective function. A simple linear model is introduced to transform the phone log-posterior probabilities output by a phe classifier to produce enhanced log-posterior features that are more suitable for the STD task. Direct optimisation of the FOM is then performed by training the parameters of this model using a non-linear gradient descent algorithm. Substantial FOM improvements of 11% relative are achieved on held-out evaluation data, demonstrating the generalisability of the approach. |
Formato |
application/pdf |
Identificador | |
Publicador |
The Institute of Electrical and Electronics Engineers, Inc |
Relação |
http://eprints.qut.edu.au/34246/1/c34246.pdf DOI:10.1109/ICASSP.2010.5494969 Wallace, Roy G., Vogt, Robert J., Baker, Brendan J., & Sridharan, Sridha (2010) Optimising figure of merit for phonetic spoken term detection. In Douglas, Scott (Ed.) Proceedings of the 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing, The Institute of Electrical and Electronics Engineers, Inc, Dallas, Texas, pp. 5298-5301. |
Direitos |
Copyright 2010 IEEE |
Fonte |
Faculty of Built Environment and Engineering; School of Engineering Systems |
Palavras-Chave | #080109 Pattern Recognition and Data Mining #Spoken Term Detection #Speech Processing #Speech Recognition #Information Retrieval |
Tipo |
Conference Paper |