@inproceedings{PougetHueberBaillyetal., author = {Pouget, Ma{\"e}l and Hueber, Thomas and Bailly, G{\´e}rard and Baumann, Timo}, title = {HMM training strategy for incremental speech synthesis}, series = {Interspeech 2015, Dresden, Germany, 6-10 September 2015}, booktitle = {Interspeech 2015, Dresden, Germany, 6-10 September 2015}, publisher = {ISCA}, doi = {10.21437/Interspeech.2015-304}, pages = {1201 -- 1205}, abstract = {Incremental speech synthesis aims at delivering the synthetic voice while the sentence is still being typed. One of the main challenges is the online estimation of the target prosody from a partial knowledge of the sentence's syntactic structure. In the context of HMM-based speech synthesis, this typically results in missing segmental and suprasegmental features, which describe the linguistic context of each phoneme. This study describes a voice training procedure which integrates explicitly a potential uncertainty on some contextual features. The proposed technique is compared to a baseline approach (previously published), which consists in substituting a missing contextual feature by a default value calculated on the training set. Both techniques were implemented in a HMM-based Text-To-Speech system for French, and compared using objective and perceptual measurements. Experimental results show that the proposed strategy outperforms the baseline technique for this language.}, language = {en} }