This paper proposes a sentence selection method using a maxi- mum entropy criterion to construct recording scripts for speech synthesis. In the conventional corpus design of speech syn- thesis, a greedy algorithm that maximizes phonetic coverage is often used. However, for statistical parametric speech syn- thesis, phonetic and prosodic contextual balance is important as well as the coverage. To take account of both of the pho- netic and prosodic contextual balance in the sentence selection, we introduce and maximize the entropy of the phonetic and prosodic contexts, such as biphone, triphone, accent, and sen- tence length. The objective experimental results show that the proposed method achieves better coverage and balance of con- texts and reduces spectral and F0 distortions compared to the random and coverage-based sentence selection methods.
|ジャーナル||Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH|
|出版ステータス||Published - 2015 1月 1|
|イベント||16th Annual Conference of the International Speech Communication Association, INTERSPEECH 2015 - Dresden, Germany|
継続期間: 2015 9月 6 → 2015 9月 10
ASJC Scopus subject areas