next up previous contents index
Next: The CRIL conventions Up: Concerning the segmentation and Previous: A caveat

Use of segmented speech databases

A segmented and labelled speech database may be used for training  the HMM models  used in many recognisers , as well as for testing  them. In addition, such a database provides the raw data needed for deriving rules for text-to-speech   synthesis  (rules of duration , intonation , formant frequencies, diphones, etc.).

A segmented and labelled speech database is also a primary resource in basic linguistic research, particularly in the case of little-researched languages. Such a database can yield fundamental information on the acoustic parameters of speech sounds of the language, as well as more detailed information on such things as patterns of duration  variation according to linguistic context.

EAGLES SWLG SoftEdition, May 1997. Get the book...