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

Chenxi Sun

Tao Sun

Wenfu Wang

Xi Chen

Lei Jia

Yunfeng Li

Guibin Wang

Qingchang Hao

Zhiping Zhou

Yutao Gai

Xiaolin Zhu

A speech synthesis method, a speech synthesis device, and an electronic apparatus are provided, which relate to a field of speech synthesis. Specific implementation solution is the following: inputting text information into an encoder of an acoustic model, to output a text feature of a current time step; splicing the text feature of the current time step with a spectral feature of a previous time step to obtain a spliced feature of the current time step, and inputting the spliced feature of the current time step into an decoder of the acoustic model to obtain a spectral feature of the current time step; and inputting the spectral feature of the current time step into a neural network vocoder, to output speech.

Speech synthesis method, speech synthesis device, and electronic apparatus

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

The disclosure provides a method, an apparatus, a device, and a computer-readable storage medium for speech synthesis in parallel. The method includes: splitting a piece of text into a plurality of segments; based on the piece of text, obtaining a plurality of initial hidden states of the plurality of segments for a recurrent neural network. The method further includes: synthesizing the plurality of segments in parallel based on the plurality of initial hidden states and input features of the plurality of segments.

Method, device, and computer-readable storage medium for speech synthesis in parallel

Growing community of inventors

Beijing, China

Chenxi Sun