PROPOR '08 Proceedings of the 8th international conference on Computational Processing of the Portuguese Language
A Style Control Technique for HMM-Based Expressive Speech Synthesis
IEICE - Transactions on Information and Systems
Accessibility of board and presentations in the classroom: a design-for-all approach
Telehealth/AT '08 Proceedings of the IASTED International Conference on Telehealth/Assistive Technologies
On the use of nonverbal speech sounds in human communication
COST 2102'07 Proceedings of the 2007 COST action 2102 international conference on Verbal and nonverbal communication behaviours
Are synthesized video descriptions acceptable?
Proceedings of the 12th international ACM SIGACCESS conference on Computers and accessibility
Expressive speech synthesis: a review
International Journal of Speech Technology
In the game: the interface between Watson and Jeopardy!
IBM Journal of Research and Development
Hi-index | 0.00 |
Expressive text-to-speech (TTS) synthesis should contribute to the pleasantness, intelligibility, and speed of speech-based human-machine interactions which use TTS. We describe a TTS engine which can be directed, via text markup, to use a variety of expressive styles, here, questioning, contrastive emphasis, and conveying good and bad news. Differences in these styles lead us to investigate two approaches for expressive TTS, a "corpus-driven" and a "prosodic-phonology" approach. Each speaker records 11 h (excluding silences) of "neutral" sentences. In the corpus-driven approach, the speaker also records 1-h corpora in each expressive style; these segments are tagged by style for use during search, and decision trees for determining f0 contours and timing are trained separately for each of the neutral and expressive corpora. In the prosodic-phonology approach, rules translating certain expressive markup elements to tones and break indices (ToBI) are manually determined, and the ToBI elements are used in single f0 and duration trees for all expressions. Tests show that listeners identify synthesis in particular styles ranging from 70% correctly for "conveying bad news" to 85% for "yes-no questions". Further improvements are demonstrated through the use of speaker-pooled f0 and duration models