Model generating method, and speech synthesis method and apparatus

An apparatus comprising:

• at least one memory configured to store computer program code;
• and
• at least one processor configured to access the at least one memory and operate according to the computer program code, the computer program code comprising:
• acquiring code configured to cause the at least one processor to acquire training speech data by concatenating speech segments having a lowest target cost among candidate concatenation solutions;
• extraction code configured to cause the at least one processor to extract training speech segments of a first annotation type, from the training speech data, the first annotation type being used for annotating that a speech continuity of a respective one of the training speech segments is superior to a preset condition;
• first calculation code configured to cause the at least one processor to calculate a mean dissimilarity matrix, based on neighboring candidate speech segments corresponding to the training speech segments before concatenation, the mean dissimilarity matrix representing a mean dissimilarity in acoustic features of groups of the neighboring candidate speech segments belonging to a same type of concatenation combination relationship;
• and
• generation code configured to cause the at least one processor to generate a concatenation cost model having a target concatenation weight, based on the mean dissimilarity matrix, the concatenation cost model corresponding to the same type of concatenation combination relationship.

A non-transitory computer-readable storage medium storing instructions that cause a processor to:

• acquire training speech data by concatenating speech segments having a lowest target cost among candidate concatenation solutions;
• extract training speech segments of a first annotation type, from the training speech data, the first annotation type being used for annotating that a speech continuity of a respective one of the training speech segments is superior to a preset condition;
• calculate a mean dissimilarity matrix, based on neighboring candidate speech segments corresponding to the training speech segments before concatenation, the mean dissimilarity matrix representing a mean dissimilarity in acoustic features of groups of the neighboring candidate speech segments belonging to a same type of concatenation combination relationship;
• and
• generate a concatenation cost model having a target concatenation weight, based on the mean dissimilarity matrix, the concatenation cost model corresponding to the same type of concatenation combination relationship.