Video Description Survey 2011 - Text-to-Speech Preferences
|
IBM Research-Japan and WGBH's Carl and Ruth Shapiro Family National Center for Accessible Media (NCAM) are conducting a joint study on the applicability of speech synthesis for video description. This is the second survey we are conducting as part of this study to solicit reactions to the use of synthesized speech to deliver descriptions of informational Web content. This study will ask you to evaluate different options for text-to-speech (TTS) description placement, content, length and speed.
Though we are conducting this study, WGBH does not intend to substitute synthesized speech for human voices on the programs and movies we currently describe. Rather, we are focusing on the potential of usingTTS technologies to increase the overall amount of described Web-based media.
The survey, accessible via screen-reading software, should take 45-60 minutes. We are eager to hear your opinions, and are grateful for your time and assistance. The survey is posted at this site. |