Hot word enhancement method and device for speech recognition and medium
A speech recognition and hot word technology, applied in the computer field, can solve the problem of end-to-end model accuracy discount, and achieve the effect of improving the recognition accuracy and improving the recognition accuracy.
Pending Publication Date: 2022-05-31
山东新一代信息产业技术研究院有限公司
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Compared with the traditional speech recognition model, the end-to-end model is more efficient and accurate in terms of training data, but in some special application scenarios beyond the scope of the training set, the accuracy of the end-to-end model is greatly reduced
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
[0024] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments of the present application and corresponding drawings. Apparently, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the scope of protection of this application.
[0025] The technical solutions provided by various embodiments of the present application will be described in detail below in conjunction with the accompanying drawings.
[0026] like figure 1 As shown, a hot word enhancement method for speech recognition provided by the embodiment of the present application is applied to a speech recognition system...
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 discloses a hot word enhancement method and device for speech recognition and a medium. The method comprises the following steps: acquiring an audio file of a hot word through an encoder, extracting features according to the audio file, and sending the extracted features to a CTC decoder so as to obtain a streaming recognition result through the CTC decoder; inputting the streaming recognition result into a language model for shallow fusion, and offsetting the recognition result according to a prefix tree to obtain a search graph; shallow fusion is carried out through WFST to obtain an optimal path according to a search graph, the optimal path is sent to an attention decoder, and an accurate result is obtained through the attention decoder to complete enhancement of the hot words. According to the method, through a hot word enhancement method combining shallow fusion of WFST, depth bias based on a prefix tree and a language model, the recognition accuracy of out-of-domain (OOD) audio is improved. And the recognition accuracy of the hot words is obviously improved.
Description
technical field [0001] The present application relates to the field of computer technology, in particular to a hot word enhancement method, device and medium for speech recognition. Background technique [0002] With the development of technology, the end-to-end automatic speech recognition model is becoming a popular choice for streaming speech recognition. Compared with the traditional speech recognition model, the end-to-end model is more efficient and accurate in terms of training data, but in some special application scenarios beyond the scope of the training set, the accuracy of the end-to-end model is greatly reduced. Contents of the invention [0003] In order to solve the above problems, the present application proposes a hot word enhancement method for speech recognition, including: obtaining the audio file of the hot word through an encoder, and extracting features according to the audio file, and sending the extracted features to A CTC decoder, to obtain a str...
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): G06F16/33G06F16/35G06F16/31G06F40/126
CPCG06F16/3343G06F16/35G06F16/322G06F40/126
Inventor 尹青山宋虎王建华高明
Owner 山东新一代信息产业技术研究院有限公司