TY  - CONF
AU  - Marçal Rusiñol
AU  - David Aldavert
AU  - Ricardo Toledo
AU  - Josep Llados
A2  - ICDAR
PY  - 2015//
TI  - Towards Query-by-Speech Handwritten Keyword Spotting
BT  - 13th International Conference on Document Analysis and Recognition ICDAR2015
SP  - 501
EP  - 505
N2  - In this paper, we present a new querying paradigm for handwritten keyword spotting. We propose to represent handwritten word images both by visual and audio representations, enabling a query-by-speech keyword spotting system. The two representations are merged together and projected to a common sub-space in the training phase. This transform allows to, given a spoken query, retrieve word instances that were only represented by the visual modality. In addition, the same method can be used backwards at no additional cost to produce a handwritten text-tospeech system. We present our first results on this new querying mechanism using synthetic voices over the George Washingtondataset.
L1  - http://refbase.cvc.uab.es/files/RAT2015b.pdf
UR  - http://dx.doi.org/10.1109/ICDAR.2015.7333812
N1  - DAG; 600.084; 600.061; 601.223; 600.077;ADAS
ID  - Marçal Rusiñol2015
ER  -