Jingdong Technology Holding Co., Ltd.

Huawei Technologies Co., Limited

Li Fu

Xiaoxiao Li

Qinghai Liang

Wei Zhu

Chiahsing Chung

Xingyang Sun

A display device control method includes when an operation on an on-screen display (OSD) input device is received, determining whether a signal generated by operating the OSD input device is currently sent to an OSD system or an operating system (OS); and when the signal generated by operating the OSD input device is currently sent to the OS, switching, according to a control signal generated by the OSD input device, the control signal from being sent to the OSD system to being sent to the OS. This application further provides a display device.

Display device control method and display device

A speech recognition method, including acquiring first linear frequency spectrums corresponding to audios to be trained with different sampling rates; determining the maximum sampling rate and other sampling rates; determining the maximum frequency domain sequence number of the first linear frequency spectrums as a first frequency domain sequence number and a second frequency domain sequence number; in the first linear frequency spectrums corresponding to the other sampling rate, configuring amplitude values corresponding to each frequency domain sequence number that is greater than the first frequency domain sequence number and less than or equal to the second frequency domain sequence number to be zero to obtain second linear frequency spectrums; determining first speech features and second voice features; and using the first speech features and the second speech features to train a machine learning model.

Speech recognition method and apparatus, and computer-readable storage medium

A method for recognizing speech comprises: respectively setting initial values of a Chinese character coefficient and a Pinyin coefficient, generating a Chinese character mapping function according to the initial value of the Chinese character coefficient, and generating a Pinyin mapping function according to the initial value of the Pinyin coefficient (S); training the Chinese character mapping function and the Pinyin mapping function using a plurality of preset training samples, calculating training results as parameters of a joint loss function, and generating a target mapping function according to calculation results (S); and recognizing, according to the target mapping function, speech to be recognized, so as to obtain a Chinese character recognition result and a Pinyin recognition result of the speech to be recognized (S). The method reduces the cost of speech recognition while ensuring the accuracy of speech recognition.

Voice recognition method and device

Eyebrow stencil

Growing community of inventors

Beijing, China

Li Fu