Baidu Online Network Technology (beijing) Co., Ltd.

Qingchang Hao

Yangyang Zhang

Jie Bai

Yunfeng Li

Xiulin Li

Guanghao Shen

Xing Luo

Xufei Jiang

Chenxi Sun

Fang Duan

Zhiping Zhou

Haiyuan Tang

Xiuzhong Gu

Yutao Gai

Wuchen Chen

A method and device for training an acoustic model are provided. The method comprises determining a plurality of tasks for training an acoustic model, obtaining resource occupancies of nodes participating in the training of the acoustic model, and distributing the tasks to the nodes according to the resource occupancies of the nodes and complexities of the tasks. By using computational resources distributed at multiple nodes, tasks for training an acoustic model are performed in parallel in a distributed manner, so as to improve training efficiency.

Method and device for training an acoustic model

A method and apparatus for synchronously playing an image and an audio are provided. The method comprises: acquiring a play service request sent by a broadcast terminal; acquiring play image data and audio data corresponding to the play service request, the play image data being divided into a plurality of groups based on played content; and sending the play image data, the audio data, and information for determining a first corresponding relationship between each of the groups and an attribute of the audio data to the broadcast terminal, to enable the broadcast terminal to perform synchronization on the play image data and the audio data correspondingly to synchronously play the play image data and the audio data. Establishing the corresponding relationship between the audio data and the played content of each of the groups enables the broadcast terminal to accurately synchronize the played audio content and the displayed play image.

Method and apparatus for synchronously playing image and audio

The present invention provides a method and a device for optimizing speech synthesis system. The method comprises: receiving speech synthesis requests contained text messages; and determining the load level of the speech synthesis system when the speech synthesis requests are received; and selecting speech synthesis paths corresponding to the load level and synthesizing the text into speech according to the speech synthesis paths.

Method and device for optimizing speech synthesis system

Growing community of inventors

Beijing, China

Qingchang Hao