A non-transitory computer-readable storage medium that stores one or more programs comprising instructions that, when executed by one or more processors of a computing device, cause the computing device to implement operations comprising:
- obtaining human voice audio data to be adjusted;
- obtaining reference human voice audio data, wherein the reference human voice audio data and the human voice audio data to be adjusted are obtained based on the same text information;
- performing framing on the human voice audio data to be adjusted and the reference human voice audio data, respectively, to obtain a first audio frame set and a second audio frame set, respectively;
- recognizing a pronunciation unit corresponding to each audio frame in the first audio frame set and the second audio frame set, respectively;
- determining, based on a timestamp of each audio frame, a timestamp of each pronunciation unit in the human voice audio data to be adjusted and the reference human voice audio data, respectively;
- and
- adjusting the timestamp of at least one pronunciation unit in the human voice audio data to be adjusted to make the timestamp of the pronunciation unit in the human voice audio data to be adjusted to be consistent with the timestamp of the corresponding pronunciation unit in the reference human voice audio data, wherein the adjusting of the timestamp comprises:
- determining a timestamp of a blank section between two words in the human voice audio data to be adjusted and a timestamp of a blank section between two words in the reference human voice audio data, based on the timestamp of each pronunciation unit in the human voice audio data to be adjusted and the reference human voice audio data, respectively;
- and
- determining a ratio of each of the at least one pronunciation unit and a ratio of the blank section, wherein the ratio of each of the at least one pronunciation unit is determined based on a ratio of a time length of the pronunciation unit in the human voice audio data to be adjusted to a time length of the corresponding pronunciation unit in the reference human voice audio data, and the ratio of the blank section is determined based on a ratio of a time length of the blank section in the human voice audio data to be adjusted to a time length of the corresponding blank section in the reference human voice audio data;
- and
- adjusting the timestamp of the pronunciation unit and the timestamp of the blank section in the human voice audio data to be adjusted based on the respective ratios to make the timestamp of the pronunciation unit in the human voice audio data to be adjusted to be consistent with the timestamp of the corresponding pronunciation unit in the reference human voice audio data and to make the timestamp of the blank section in the human voice audio data to be adjusted to be consistent with the timestamp of the blank section in the reference human voice audio data.