METHOD AND SYSTEM OF PRODUCING NATURAL-SOUNDING RECITATION OF STORY IN PERSON™S VOICE AND ACCENT

摘要

Disclosed is a method of producing a natural-sounding recitation of a story in a person™s voice and accent. The method comprises obtaining an audio of the person™s utterance of words of a text content, the text content being different from a story text of the story, extracting from the audio individual audio frames of speech units of the given natural language occurring in the given word and/or sentence, concatenating the extracted audio frames of the speech units occurring in the given word and/or sentence to produce a voice- synthesized audio of the given word and/or sentence in the person™s voice and accent, and employing a predefined time gap profile to insert different time gaps between different pairs of words occurring substantially consecutively in the story text, when producing the recitation of the story in the person™s voice and accent.