Title :
Searching with a transcription graph
Author :
Li, Z. ; Kenny, P. ; Shaughnessy, D.O.
Author_Institution :
INRS-Telecommun., Quebec Univ., Verdun, Que., Canada
Abstract :
We present new developments in our approach to the search problem in very large vocabulary speech recognition. A transcription graph, which encodes all high scoring phonetic transcriptions which satisfy lexical constraints, is built so as to completely separate the search of the lexicon from the construction of the word graph. This enables us to limit the computational burden of searching in a way which is essentially independent of the size of the language model
Keywords :
data structures; graph theory; natural languages; search problems; speech coding; speech processing; speech recognition; encoding; high scoring phonetic transcriptions; language model; lexical constraints; search problem; transcription graph; very large vocabulary speech recognition; word graph; Buildings; Business; Costs; Data structures; Dictionaries; Search problems; Speech recognition; Tree graphs; Viterbi algorithm; Voting;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-2431-5
DOI :
10.1109/ICASSP.1995.479660
