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

Boe Technology Group Co., Ltd.

Beijing Boe Display Technology Co., Ltd.

Hesel Xiongan Kecheng Inspection and Certification Co., Ltd.

Beijing No.6 Construction Engineering Quality Test Department Co., Ltd

Beijing Building Research Institute Corporation Limited of Cscec

Xuewei Zhang

Xiangang Li

Rui Zhang

Jie Yang

Xiaoxiao Li

Mingchao Wang

Changjun Wang

Hefei Li

Sen Pang

Dandan Xu

Xupeng Zhang

Yingkun Wang

Xiaohe Gan

Zihang Jiang

A prestressed fish-belly reaction frame, a pile foundation bearing capacity detection device and application thereof, which includes: a core junction; a reaction beam including a plurality of beam units symmetrically arranged around the core junction with the core junction as a center, each beam unit has a first end and a second end, the first end is connected and fixed to the core junction, and the second end is connected and fixed to a pile top of an anchor pile when the pile foundation bearing capacity is detected; a prestressed assembly including a plurality of prestressed tendons, each prestressed tendon passes through an upper end of the core junction, a first end of each prestressed tendon is connected and fixed to the second end of one beam unit, a second end thereof is connected and fixed to the second end of the symmetrical beam unit.

Prestressed fish-belly reaction frame, pile foundation bearing capacity detection device and application thereof

A virtual display apparatus includes: a flexible display component layer having a light exit surface and a non-light exit surface opposite to the light exit surface; a lens layer disposed at the light exit surface of the flexible display component layer, and configured to converge light; a curvature adjustment layer disposed on the non-light exit surface of the flexible display component layer. The lens layer has a first surface facing the flexible display component layer, and the first surface of the lens layer and the light exit surface of the flexible display component layer have a gap therebetween. The curvature adjustment layer is configured to deform in response to at least one deformation signal, so as to adjust distances between the first surface of the lens layer and different positions of the light exit surface of the flexible display component layer along a thickness direction of the lens layer.

Virtual display apparatus, and methods of manufacturing and controlling the same

Embodiments of the present disclosure provide a method and a device for recognizing a speech based on a Chinese-English mixed dictionary. The method includes acquiring a Chinese-English mixed dictionary marked by an international phonetic alphabet, in which, the Chinese-English mixed dictionary includes a Chinese dictionary and an English dictionary revised by Chinglish; by taking the Chinese-English mixed dictionary as a training dictionary, taking a one-layer Convolutional Neural Network and a five-layer Long Short-Term Memory as a model, taking syllables or words as a target and taking a connectionist temporal classifier as a training criterion, training the model to obtain a trained CTC acoustic model; and performing a speech recognition on a Chinese-English mixed language based on the trained CTC acoustic model.

Method and device for recognizing speech based on Chinese-English mixed dictionary

Embodiments of the present disclosure provide a method and a device for recognizing a speech based on a Chinese-English mixed dictionary. The method includes acquiring a Chinese-English mixed dictionary marked by an international phonetic alphabet, in which, the Chinese-English mixed dictionary includes a Chinese dictionary and an English dictionary revised by Chinglish; by taking the Chinese-English mixed dictionary as a training dictionary, taking a one-layer Convolutional Neural Network and a five-layer Long Short-Term Memory as a model, taking a state of the IPA as a target and taking a connectionist temporal classifier as a training criterion, training the model to obtain a trained CTC acoustic model; and performing a speech recognition on a Chinese-English mixed language based on the trained CTC acoustic model.

The present disclosure provides a method and a device for eliminating background sound, and a terminal device. The method includes: obtaining an initial audio data set; performing background sound fusion processing on the initial audio data set to obtain training sample data; performing neural network training based on the training sample data and the initial audio data set to generate an initial neural network model for eliminating background sound; and performing background sound elimination on audio data to be processed based on the initial neural network model for eliminating background sound.

Method and device for eliminating background sound, and terminal device

Growing community of inventors

Beijing, China

Xuewei Zhang