Speech and Vision Lab

  • Increase font size
  • Default font size
  • Decrease font size
Home Publications Advanced Publication Search
IIIT-H SWS 2013: Gaussian Posteriorgrams of Bottle-Neck Features for Query-by-Example Spoken Term Detection
Research Area: Uncategorized Year: 2013
Type of Publication: In Proceedings Keywords: Query by example spoken term detection, multi layer perceptron, articulatory features, bottle neck features, low resource
Authors: Gautam Varma Mantena, Kishore S. Prahallad  
   
Abstract:
This paper describes the experiments conducted for spoken web search (SWS) at MediaEval 2013 evaluations. A conventional approach is to train a multi-layer perceptron using high resource languages and then use it in the low resource scenario. However, phone posteriorgrams have been found to under-perform when the language they were trained on differs from the target language. In this paper, we use bottle-neck features derived from MLP to generate Gaussian posteriorgrams. We also use a variant of dynamic time warping (DTW) based technique which exploits the redundancy in speech signal and thus averages the successive Gaussian posteriorgrams to reduce the length of the spoken query and spoken reference.
Digital version