Beijing Baidu Netcom Science Technology Co., Ltd

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

Zhipeng Nie

Tao Sun

Lei Jia

Liqiang Zhang

Jiankang Hou

Haifeng Wang

Changbin Chen

Yanyao Bian

Zhanjie Gao

A method for processing a speech includes: acquiring an original speech; extracting a spectrogram from the original speech; acquiring a speech synthesis model, where the speech synthesis model comprises a first generation sub-model and a second generation sub-model; generating a harmonic structure of the spectrogram, by invoking the first generation sub-model to process the spectrogram; and generating a target speech, by invoking the second generation sub-model to process the harmonic structure and the spectrogram.

Method and apparatus for processing speech, electronic device and storage medium

A method of processing audio data, an electronic device, and a storage medium, which relates to a field of artificial intelligence, in particular to a field of speech processing technology. The method includes: processing spectral data of the audio data to obtain a first feature information; obtaining a fundamental frequency indication information according to the first feature information, wherein the fundamental frequency indication information indicates valid audio data of the first feature information and invalid audio data of the first feature information; obtaining a fundamental frequency information and a spectral energy information according to the first feature information and the fundamental frequency indication information; and obtaining a harmonic structure information of the audio data according to the fundamental frequency information and the spectral energy information.

Method of processing audio data, electronic device and storage medium

This application discloses a prosodic pause prediction method, a prosodic pause prediction device and an electronic device. The specific implementation scheme includes: obtaining a first matrix by mapping a to-be-tested text sequence through a trained embedding layer, where the to-be-tested text sequence includes a to-be-tested input text and an identity of a to-be-tested speaker; inputting the first matrix into a trained attention model, and determining a semantic representation matrix by the trained attention model; and, performing prosodic pause prediction based on the semantic representation matrix and outputting a prosodic pause prediction result of each word in the to-be-tested input text.

Prosodic pause prediction method, prosodic pause prediction device and electronic device

Growing community of inventors

Beijing, China

Zhipeng Nie