|
Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1842/1079
|
| Title: | Named Entity Extraction from Word Lattices |
| Authors: | Horlock, James
King, Simon |
| Issue Date: | 2003 |
| Citation: | Horlock, James / King, Simon (2003): "Named entity extraction from word lattices", In EUROSPEECH-2003, 1265-1268. |
| Publisher: | International Speech Communication Association |
| Abstract: | We present a method for named entity extraction from word lattices produced by a speech recogniser. Previous work by others on named entity extraction from speech has used either a manual transcript or 1-best recogniser output. We describe how a single Viterbi search can recover both the named entity sequence and the corresponding word sequence from a word lattice, and further that it is possible to trade off an increase in word error rate for improved named entity extraction. |
| Keywords: | Speech Recognition
Viterbi search |
| URI: | http://www.isca-speech.org/archive/eurospeech_2003/index.html
http://hdl.handle.net/1842/1079 |
| Appears in Collections: | CSTR publications
|
Items in ERA are protected by copyright, with all rights reserved, unless otherwise indicated.
|
