Automatic exploration of corpus-specific properties for expressive text-to-speech: a case study in emphasis
Automatic exploration of corpus-specific properties for expressive text-to-speech: a case study in emphasis
复制标题
自动探索表达性文本转语音的语料库特定属性：重点案例研究
DOI：
--
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
B. Ramabhadran
中科院分区：
文献类型：
--
作者：
Raul Fernandez;B. Ramabhadran
在本文中，我们探索了一种表达性文本到语音合成的方法，其中预先存在的特定表达语料库与自动生成的标签相补充，以扩大引擎可利用的单元的搜索空间，以提高其表达力。我们将这种数据发现方法作为数据收集指导方法的替代方法，以便充分利用合成语料库中已包含的表达能力。我们通过一个案例研究来说明该方法，该案例研究使用强调作为其预期表达，描述自动发现数据库中此类实例的算法以及如何在综合过程中使用它们，最后评估该提案的好处以证明该方法的可行性。
In this paper we explore an approach to expressive text-tospeech synthesis in which pre-existing expression-specific corpora are complemented with automatically generated labels to augment the search space of units the engine can exploit to increase its expressiveness. We motivate this data-discovery approach as an alternative to an approach guided by data collection, in order to harness the full usefulness of the expressiveness already contained in a synthesis corpus. We illustrate the approach with a case study that uses emphasis as its intended expression, describe algorithms for the automatic discovery of such instances in the database and how to make use of them during synthesis, and, finally, evaluate the benefits of the proposal to demonstrate the feasibility of the approach.