Beijing Xiaomi Mobile Software Co., Ltd.

Beijing Institute of Nanoenergy and Nanosystems

Long Lin

Jun Chen

Wei Kang

Zhonglin Wang

Liyong Guo

Fangjun Kuang

Mingshuang Luo

Guang Zhu

Zengwei Yao

Povey Daniel

Quandong Wang

Yuxiang Kong

Daniel Povey

Sihong Wang

The present disclosure provides a method and apparatus for training a neural network, and a method and apparatus for audio processing. The method includes: encoding training audio data input to an encoder network to obtain a first encoding result, and predicting a text label corresponding to the training audio data input to a prediction network to obtain a first prediction result; jointing the first encoding result with the first prediction result to obtain a first joint result; pruning the first encoding result and the first prediction result according to the first joint result to obtain a second encoding result and a second prediction result; performing a joint processing on the second encoding result and the second prediction result input to a joiner network to obtain a second joint result, and adjusting network parameters of the encoder network, the prediction network and the joiner network according to the second joint result.

Method and apparatus for training neural network, and method and apparatus for audio processing

A method and apparatus for audio processing, an electronic device and a storage medium are provided. The method includes: obtaining an audio encoding result, wherein each element in the audio encoding result has a coordinate in an audio frame number dimension and a coordinate in a text label sequence dimension; in response to an output result of an iframe in a decoding path being a non-null character, respectively increasing the coordinate in the audio frame number dimension and the coordinate in the text label sequence dimension corresponding to an output position of the iframe by 1 to obtain an output position of a (i+1)frame in the decoding path; and determining an output result corresponding to the output position of the (i+1)frame according to the output result of the iframe in the decoding path and an element of the (i+1)frame in the audio encoding result.

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

A method of training a speech recognition model is provided. The method includes that: speech data of each of a plurality of training samples is inputted into a teacher model and a to-be-trained speech recognition model separately. Additionally, an embedding outputted by the teacher model and encoded data outputted by the to-be-trained speech recognition model are obtained. Furthermore, quantized codebook data is obtained by performing a multi-codebook quantization on the embedding. A loss is calculated based on the encoded data, the quantized codebook data, and text data in the training sample. Moreover, a trained speech recognition model is obtained by stopping training the to-be-trained speech recognition model when the loss is less than or equal to a preset loss threshold and/or trained times is greater than preset trained times.

Method of training speech recognition model, electronic device and storage medium

Growing community of inventors

Beijing, China

Long Lin