Beijing Jingdong Century Trading Co., Ltd.

Beijing Wodong Tianjun Information Technology Co., Ltd.

Yuyu Cai

Junyi Wu

Fan Yang

Wei Song

Xiaodong He

Zhengchen Zhang

Xin Yuan

Wuyang Cui

Gang Quan

Guohong Ding

A custom tone and vocal synthesis method and apparatus, an electronic device, and a storage medium. The synthesis method comprises: training a first neural network by means of a speaker record sample to obtain a speaker recognition model, the output training result of the first neural network being a speaker vector sample (S); training a second neural network by means of an unaccompanied vocal singing sample and the speaker vector sample to obtain an unaccompanied singing synthesis model (S); inputting a speaker record to be synthesized into the speaker recognition model to obtain speaker information output by the intermediate hidden layer of the speaker recognition model (S); and inputting unaccompanied singing music information to be synthesized and the speaker information into the unaccompanied singing synthesis model to obtain a synthesized custom tone and vocal (S).

Custom tone and vocal synthesis method and apparatus, electronic device, and storage medium

The present disclosure relates to a decoding method, apparatus and computer-readable storage medium, which relates to the field of computer technology. The method of the present disclosure includes buffering one or more stream segments of a data stream which are received, wherein the data stream comprises an audio stream; parsing the one or more stream segments buffered until header information is obtained through the parsing; storing the header information; and decoding stream segments of the audio stream among various stream segments received according to the header information until the audio stream is completely decoded.

Decoding method and apparatus, and computer readable storage medium

Growing community of inventors

Beijing, China

Yuyu Cai