Beijing Dajia Internet Information Technology Co., Ltd.

Kwai Inc.

Xiaorui Wang

Qiang Li

Yang Liu

Lingzhi Liu

Yongxiong Ren

Heng Liu

Yan Li

Luo Zhang

Zhidong Lang

Yuanyuan Zhao

Kaituo Xu

An automatic speech recognition system and a method thereof are provided. The system includes an encoder and a decoder. The encoder comprises a plurality of encoder layers. At least one encoder layer includes a plurality of encoder sublayers fused into one or more encoder kernels. The system further comprises a first pair of ping-pong buffers communicating with the one or more encoder kernels. The decoder comprises a plurality of decoder layers. At least one decoder layer includes a plurality of decoder sublayers fused into one or more decoder kernels. The decoder receives a decoder output related to the encoder output and generates a decoder output. The encoder sends the decoder output to a beam search kernel.

Systems and methods for automatic speech recognition based on graphics processing units

The present disclosure relates to an automatic speech recognition system and a method thereof. The system includes a conformer encoder and a pair of ping-pong buffers. The encoder includes a plurality of encoder layers sequentially executed by one or more graphic processing units. At least one encoder layer includes a first feed forward module, a multi-head self-attention module, a convolution module, and a second feed forward module. The convolution module and the multi-head self-attention module are sandwiched between the first feedforward module and the second feed forward module. The four modules respectively include a plurality of encoder sublayers fused into one or more encoder kernels. The one or more encoder kernels respectively read from one of the pair of ping-pong buffers and write into the other of the pair of ping-pong buffers.

Disclosed are a method, device and readable storage medium for speech recognition. The method includes: determining speech features of the speech data by feature extraction on the speech data; determining syllable data corresponding to each of the speech features based on a plurality of feature extraction layers and a softmax function layer included in an acoustic model, where the acoustic model is configured to convert the speech feature into the syllable data; determining text data corresponding to the speech data based on a language model, a pronouncing dictionary and the syllable data, where the pronouncing dictionary is configured to convert the syllable data into the text data, and the language model is configured to evaluate the text data; and outputting the text data.

Method, device and storage medium for speech recognition

Disclosed are a method, an electronic device, and a computer readable storage medium for creating a vote. The method includes: receiving a vote initiation instruction to obtain voice information inputted currently; determining textual information by recognizing the voice information; determining at least two option words based on semantic recognition of the textual information; generating a question stem of the vote based on the textual information; and generating voting options based on the option words for the vote.

Method, electronic device, and computer readable storage medium for creating a vote

Growing community of inventors

Beijing, China

Xiaorui Wang