Abstract | ||
---|---|---|
We describe techniques used in the development of an automaticannotation system for use with a concatenative text-to-speechsynthesis system. The goal of the system is to generate automaticallyfrom word-level transcriptions annotations that resultin synthetic speech of the same quality as that produced fromhand-labelled speech. Our approach in this work has been touse the standard technique of "forced-alignment" to each utteranceand to refine both acoustic and pronunciation modellingto... |
Year | Venue | Field |
---|---|---|
1998 | ICSLP | Annotation,Automatic image annotation,Pattern recognition,Computer science,Image retrieval,Speech recognition,Artificial intelligence |
DocType | Citations | PageRank |
Conference | 6 | 0.60 |
References | Authors | |
5 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stephen Cox | 1 | 188 | 16.61 |
Richard Brady | 2 | 6 | 0.60 |
Peter Jackson | 3 | 56 | 6.99 |