Timbre selection method and apparatus, electronic device, readable storage medium, and program product

An electronic device, comprising:

• a memory and a processor;
• wherein the memory is configured to store computer program instructions;
• and the processor is configured to execute the computer program instructions, to implement operations comprising:
• performing spectral feature extraction on a speech of a voice role among a plurality of voice roles to obtain a spectral feature of the voice role;
• performing timbre feature extraction on the spectral feature of the voice role to obtain a timbre feature of the voice role;
• determining a target sample audio from at sample audio library as a dubbing timbre for the voice role based on the timbre feature of the voice role and a timbre feature of at least one initial sample audio in the sample audio library, wherein a timbre of the target sample audio matches the timbre feature of the voice role;
• and
• generating a dubbed audio for the voice role based on the target sample audio that has the same timber style as the speech of the voice role.

A non-transitory readable storage medium, comprising:

• computer program instructions;
• wherein the computer program instructions, when executed by at least one processor, cause the at least one processor to perform operations comprising:
• performing spectral feature extraction on a speech of a voice role among a plurality of voice roles to obtain a spectral feature of the voice role;
• performing timbre feature extraction on the spectral feature of the voice role to obtain a timbre feature of the voice role;
• determining a target sample audio from at sample audio library as a dubbing timbre for the voice role based on the timbre feature of the voice role and a timbre feature of at least one initial sample audio in the sample audio library, wherein a timbre of the target sample audio matches the timbre feature of the voice role;
• and
• generating a dubbed audio for the voice role based on the target sample audio that has the same timber style as the speech of the voice role.