Method for outputting speech data with consistent speech style, electronic device, and storage medium

A method for outputting speech data, comprising:

• sending, in response to detecting that an interaction content to be proceeded by a virtual game character comprises a name of the virtual game character, sending, by a client, a target request to a server, wherein information carried in the target request comprises a target text, and the target text is configured to represent the name of the virtual game character;
• acquiring, by the client, first speech data, wherein the first speech data is obtained by the server by converting the target text in response to the target request;
• obtaining, by the client, third speech data by splicing the first speech data and second speech data, wherein the second speech data comprises a content other than the name of the virtual game character in the interaction content;
• and
• playing, by the client, the third speech data with a consistent speech style;
• wherein converting the target text into the first speech by the server, comprises:
• obtaining, by the server, style information of the second speech data, comprising:
• extracting a first acoustic feature of the second speech data;
• and
• determining the style information based on the first acoustic feature, wherein the
• style information is configured to represent a speech style of the second speech data;
• extracting a text feature of the target text;
• obtaining an alignment result by aligning the text feature and the first acoustic feature;
• and
• converting the style information and the alignment result into the first speech data, wherein a speech style of the first speech data is the same as the speech style of the second speech data.

An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable by the processor, and the processor is configured to:

• receive a target request from a client, wherein information carried in the target request comprises a target text, and the target text is configured to represent a name of a virtual game character;
• convert the target text into first speech data in response to the target request;
• and
• send the first speech data to the client, wherein the first speech data is used by the client to output and play a third speech data with a consistent speech style, the third speech data is obtained by splicing the first speech data with second speech data, and the second speech data comprises a content other than the name of the virtual game character in an interaction content to be proceeded by the virtual game character;
• wherein the processor is configured to:
• extract a first acoustic feature of the second speech data;
• and
• determine the style information based on the first acoustic feature to obtain style information of the second speech data, wherein the style information is configured to represent a speech style of the second speech data;
• wherein the processor is further configured to convert the target text into the first speech by:
• extracting a text feature of the target text;
• obtaining an alignment result by aligning the text feature and the first acoustic feature;
• and
• converting the style information and the alignment result into the first speech data, wherein a speech style of the first speech data is the same as the speech style of the second speech data.