next up previous contents index
Next: ITU-T Overall Quality Test Up: Conclusion: summary of test Previous: SAM Prosodic Function Test

 

SAM Overall Quality Test

   

Status Completely developed software (in SOAP)  allowing the use of the magnitude and categorical estimation    scaling methods. Two variants are recommended: 20-point categorical estimation   without reference (for test internal comparison) and magnitude estimation  by line length, with imaginary ideal speech as a reference (for test external comparison) [Chapter 7]Howard-Jones92a.
Goal Comparative evaluation of overall quality  aspects, particularly acceptability, intelligibility, and naturalness , for longer stretches of speech.
Languages In principle applicable to any language as long as suitable stimulus material is available.
Items Eight lists of 20 meaningful sentences of varying syntactic structures and length. For the rating of intelligibility and naturalness , speech material is available for Dutch, English, French, German, Italian, and Swedish. One list is sufficient for the evaluation of a synthesiser. Examples: I realise you're having supply problems, but this is rather excessive and I need to arrive by 10.30 a.m. on Saturday.
Procedure Each aspect of speech is rated by a different group of subjects (minimally ten). When rating acceptability, it is recommended that application specific speech materials are presented to (prospective) users. The ratings are based on two sentences each time.
Time With 160 sentences and a 5 sec interstimulus interval, the rating of one scale takes about 20 min.
Analysis Automatic.



next up previous contents index
Next: ITU-T Overall Quality Test Up: Conclusion: summary of test Previous: SAM Prosodic Function Test

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