Alibaba Group Holding Limited

Alibaba Damo (hangzhou) Technology Co., Ltd.

Shiliang Zhang

Ming Lei

Wei Li

Haitao Yao

Zhifu Gao

Weilong Huang

Siqi Zheng

A method, an apparatus, and an electronic device for streaming end-to-end speech recognition are described. The method includes: extracting and encoding speech acoustic features of a received voice stream in units of frames; performing block processing, and predicting a number of activation points included in a same block that need to be encoded and outputted; determining position(s) of activation point(s) that need(s) to be decoded and outputted according to a prediction result, to a decoder to perform decoding at the position(s) of the activation point(s) and output a recognition result. Through the embodiments of the present disclosure, the robustness of a streaming end-to-end speech recognition system to noise can be improved, thereby improving the performance and the accuracy of the system.

Streaming end-to-end speech recognition method, apparatus and electronic device

A speech processing method, a speech encoder, a speech decoder, and a speech recognition system are provided. The method includes: obtaining a speech signal to be processed; using a first neural network and a second neural network to process the speech signal to obtain first feature information and second feature information corresponding to the speech signal respectively, wherein a computational efficiency of the first neural network is higher than a computational efficiency of the second neural network, and an accuracy of the second feature information outputted by the second neural network is higher than an accuracy of the first feature information outputted by the first neural network; and determining target feature information used to represent semantics in the speech signal based on the first feature information and the second feature information.

Speech processing method, speech encoder, speech decoder and speech recognition system

Embodiments of the disclosure provide a method and system for speech recognition. The method comprises dividing space into a plurality of regions based on preset DOA angles to allocate a signal source to the plurality of regions, wherein signals in the plurality of regions are enhanced and recognized, the result of which are fused to obtain a recognition result of the signal source.

Method and system for speech recognition

The present disclosure discloses a sound detection method. The method includes: obtaining an initial sound signal and a spatial distribution spectrum of the initial sound signal; segmenting the initial sound signal, to obtain a target sound segment, and obtaining a timestamp corresponding to the target sound segment, the target sound segment including a speech of at least one object, and the timestamp being used for indicating a start time of the target sound segment and an end time of the target sound segment; segmenting the spatial distribution spectrum by using the timestamp, to obtain a spatial distribution spectrum segment corresponding to the target sound segment; and inputting the target sound segment and the spatial distribution spectrum segment into a sound detection model, to obtain a first sound detection result, the first sound detection result being used for describing whether sound of multiple objects exists in the initial sound signal.

Sound detection method

In various embodiments, this application provides an audio information processing method, an audio information processing apparatus, an electronic device, and a storage medium. An audio information processing method in an embodiment includes: obtaining a first audio feature corresponding to audio information; performing, based on an audio feature at a specified moment in the first audio feature and audio features adjacent to the audio feature at the specified moment, an encoding on the audio feature at the specified moment to obtain a second audio feature corresponding to the audio information; obtaining decoded text information corresponding to the audio information; and obtaining, based on the second audio features and the decoded text information, text information corresponding to the audio information. According to this method, fewer parameters are used in the process of obtaining the second audio feature and obtaining, based on the second audio feature and the decoded text information, the text information corresponding to the audio information, thereby reducing computational complexity in the audio information processing process and improving audio information processing efficiency.

Audio information processing method, audio information processing apparatus, electronic device, and storage medium

Embodiments of the present disclosure provide methods and systems for processing a speech signal. The method can include: processing the speech signal to generate a plurality of speech frames; generating a first number of acoustic features based on the plurality of speech frames using a frame shift at a given frequency; and generating a second number of posteriori probability vectors based on the first number of acoustic features using an acoustic model, wherein each of the posteriori probability vectors comprises probabilities of the acoustic features corresponding to a plurality of modeling units, respectively.

Growing community of inventors

Hangzhou, China

Shiliang Zhang