Sie befinden Sich nicht im Netzwerk der Universität Paderborn. Der Zugriff auf elektronische Ressourcen ist gegebenenfalls nur via VPN oder Shibboleth (DFN-AAI) möglich. mehr Informationen...
Improved spoken term detection using support vector machines based on lattice context consistency
Ist Teil von
2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2011, p.5648-5651
Ort / Verlag
IEEE
Erscheinungsjahr
2011
Quelle
IEEE Xplore
Beschreibungen/Notizen
We propose an improved spoken term detection approach that uses support vector machines trained with lattice context consistency. The basic idea is that the same term usually have similar context, while quite different context usually implies the terms are different. Support vector machine can be trained using query context feature vectors obtained from the lattice to estimate better scores for ranking, and significant improvements can be obtained. This process can be performed iteratively and integrated with the pseudo relevance feedback in acoustic feature space proposed previously, both offering further improvements.