US 12,456,452 B2
Text data processing method and apparatus
Nianzu Zheng, Shenzhen (CN); Disong Wang, Shenzhen (CN); Liqun Deng, Shenzhen (CN); and Yang Zhang, Shenzhen (CN)
Assigned to Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed by HUAWEI TECHNOLOGIES CO., LTD., Guangdong (CN)
Filed on Jul. 21, 2023, as Appl. No. 18/356,738.
Application 18/356,738 is a continuation of application No. PCT/CN2022/072441, filed on Jan. 18, 2022.
Claims priority of application No. 202110091046.9 (CN), filed on Jan. 22, 2021.
Prior Publication US 2023/0360634 A1, Nov. 9, 2023
Int. Cl. G10L 13/08 (2013.01); G10L 25/30 (2013.01)
CPC G10L 13/08 (2013.01) [G10L 25/30 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
obtaining target text, wherein a phoneme of the target text comprises a first phoneme and a second phoneme that is adjacent to first phoneme;
performing feature extraction on the first phoneme and the second phoneme to obtain a first audio feature of the first phoneme and a second audio feature of the second phoneme;
obtaining, by using a target recurrent neural network (RNN) and based on the first audio feature, first speech data corresponding to the first phoneme, and obtaining, by using the target RNN and based on the second audio feature, second speech data corresponding to the second phoneme, wherein the first speech data and the second speech data are concurrently obtained; and
obtaining, by using a vocoder and based on the first speech data and the second speech data, audio corresponding to the first phoneme and audio corresponding to the second phoneme.