Speech recognition model training method, speech recognition method and device
A speech recognition model and speech recognition technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of inability to recognize speech, speech aliasing, and reducing the accuracy of speech recognition.
Active Publication Date: 2021-08-31
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, in most scenarios, there may be multi-person conversations, resulting in aliasing between voices, which increases the difficulty of voice recognition and reduces the accuracy of voice recognition, and may even lead to unrecognizable voices
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0031] Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and they should be regarded as exemplary only. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
[0032] figure 1 is a structural diagram of a speech recognition model according to an exemplary embodiment of the present disclosure.
[0033] The speech recognition model 100 may be configured to perform speech recognition based on input sound samples / audio features 10 of the sound samples to obtain a speech recognition result 30 . The audio feature 10 of the sound s...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides a speech recognition model training method, and a speech recognition method and device, and relates to the field of deep learning and natural speech processing, in particular to a speech recognition technology based on deep learning. According to the specific implementation scheme, the speech recognition model comprises an extraction sub-model and a recognition sub-model. The training method comprises the steps: inputting audio features of a first training audio sample into the speech recognition model, enabling the recognition sub-model to receive spokesman features from the extraction sub-model, and recognizing the received audio features based on the spokesman features and parameters of the recognition sub-model to obtain a recognition result; calculating a first loss value for the recognition result based on a loss function of the recognition sub-model and labeling information corresponding to the first training audio sample; and adjusting model parameters according to the first loss value until the first loss value converges.
Description
technical field [0001] The present disclosure relates to the fields of deep learning and natural speech processing, in particular, to a speech recognition technology based on deep learning, and more specifically, to a speech recognition model training method, speech recognition method and device. Background technique [0002] With the advancement of artificial intelligence technology, speech recognition technology is widely used in various scenarios. However, in most scenarios, there may be multi-person conversations, resulting in aliasing between voices, which increases the difficulty of voice recognition and reduces the accuracy of voice recognition, and may even lead to unrecognizable voices. [0003] Therefore, there is a need for a speech recognition model, a speech recognition method and a speech recognition device, which can accurately perform speech recognition in multi-person dialogue scenarios. Contents of the invention [0004] The present disclosure provides a...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G10L15/06G10L15/16
CPCG10L15/063G10L15/16G10L2015/0631
Inventor 赵情恩
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD