Microsoft Technology Licensing, LLC

Tsinghua University

Nuctech Company Limited

Petrochina Company Limited

Yanqing Liu

Sheng Zhao

Wei Zhang

Yuanjing Li

Yinong Liu

Jun Li

Jinyu Li

Yulan Li

Hao Jiang

Lan Zhang

Bin Yao

Zijian Wang

Yulin Li

Jianqiang Fu

Yafeng Ju

Jiuzheng Yu

Lingzhi Yang

Fuwei Bi

Bilin Luo

Xiaoqiang Wang

Jinzhu Li

Guangyu Wu

Systems and methods are provided for generating a lightweight, high-quality streaming text-to-speech (TTS) system. For example, some disclosed systems are configured to obtain a first model comprising one or more layers of a convolutional neural network. Each layer of the convolutional neural network is configured to generate a new output from a previous input. The systems also obtain a second model comprising a recurrent neural network. Subsequent to obtaining the first model and the second model, the systems are configured to compile the one or more layers of the convolutional neural network and the recurrent neural network in a parallel architecture to generate a machine learning module such that each model of the machine learning module is configured to receive input simultaneously.

Streaming, lightweight and high-quality device neural TTS system

Novel solutions for speech recognition provide contextual spelling correction (CSC) for automatic speech recognition (ASR). Disclosed examples include receiving an audio stream; performing an ASR process on the audio stream to produce an ASR hypothesis; receiving a context list; and, based on at least the ASR hypothesis and the context list, performing spelling correction to produce an output text sequence. A contextual spelling correction (CSC) model is used on top of an ASR model, precluding the need for changing the original ASR model. This permits run-time user customization based on contextual data, even for large-size context lists. Some examples include filtering ASR hypotheses for the audio stream and, based on at least the ASR hypotheses filtering, determining whether to trigger spelling correction for the ASR hypothesis. Some examples include generating text to speech (TTS) audio using preprocessed transcriptions with context phrases to train the CSC model.

Contextual spelling correction (CSC) for automatic speech recognition (ASR)

A layered water injection system and a layered water injection method. The system comprises: a ground water injection valve group configured with an intelligent control valve, for receiving a water injection control instruction sent by a remote control center, and for converting the water injection control instruction into a switching action of the intelligent control valve to control water flow pressure fluctuation in a water injection string, so as to form a first pressure wave code in the water injection string; a water distributor for collecting the first pressure wave code, interpreting the first pressure wave code as a corresponding water outlet switch instruction, and performing layered water injection control according to the water outlet switch instruction. The embodiments of the application can improve the automation level of layered water injection and the reliability of layered water injection control.

Layered water injection system and layered water injection method

A radiation detector is provided. The radiation detection comprises a semiconductor crystal for detecting radiation. The semiconductor crystal comprises a top surface, a bottom surface, and at least one side surface. At least one anode is arranged on at least one of the top surface, the bottom surface, and the at least one side surface. At least one cathode is arranged on at least another one of the top surface, the bottom surface, and the at least one side surface. The at least one anode each has a stripe shape, the at least one cathode each has a planar or curved shape, and the at least one cathode and the at least one anode extend in parallel with respect to each other to a length substantially equal to that of the anode. Such an electrode structure can improve energy resolution and detection efficiency of the radiation detector effectively.

Radiation detector

Growing community of inventors

Beijing, China

Yanqing Liu