Second European Conference on Speech Communication and Technology

Genova, Italy
September 24-26, 1991


Word Spotting by CSR Through Vector Quantized Background Models

Alessandro Falaschi, Alfredo Micozzi

La Sapienza University of Rome, INFO-COM Dpt. , Roma, Italy

A simple solution to the word spotting problem is experimented. Continuous Speech Recognition (CSR) techniques are adopted, with the background speech represented by a filler templates set defined through vector quantization algorithms. Quantitative results about the performed experiments are given. Keywords: Word Spotting, Continuous Speech Recognition, Vector Quantization.

Full Paper

Bibliographic reference.  Falaschi, Alessandro / Micozzi, Alfredo (1991): "Word spotting by CSR through vector quantized background models", In EUROSPEECH-1991, 1187-1190.