Voice recognition method and device

A speech recognition and speech data technology, applied in speech recognition, speech analysis, unstructured text data retrieval, etc., can solve the problem of inability to customize, and achieve the goal of improving recognition accuracy, improving speech recognition effect, and improving recognition effect. Effect

Pending Publication Date: 2020-07-17
BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The training of the customized model needs to obtain a large amount of relevant corpus of the application scenario in advance, but for some conferences and other scenarios, because the specific content of the speeches of the participants cannot be obtained in advance, the customization cannot be carried out.

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Voice recognition method and device
  • Voice recognition method and device
  • Voice recognition method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to enable those skilled in the art to better understand the solutions of the embodiments of the present invention, the embodiments of the present invention will be further described in detail below in conjunction with the drawings and implementations.

[0046] In some application scenarios where the model cannot be pre-customized, such as meeting scenarios, if the general language model is used for speech recognition, the recognition effect is not ideal, especially for entity words such as person names, place names, product names, and some professional nouns contained in the speech data. In some cases, recognition errors often occur, and errors in speech recognition will lead to errors in subsequent machine translations.

[0047] For example: Regarding Gaussian, whether Gaussian here is a person's name or a Gaussian function on data, the translations of the two are completely different;

[0048] For example: Xiaoai speaker, when this product first appeared, w...

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

No PUM Login to view more

Abstract

The invention discloses a voice recognition method and device. The method comprises the steps: receiving voice data of a speaker, and acquiring a text material related to the voice data; extracting akeyword in the text material; and performing voice recognition on the voice data by using a decoding network, adjusting scores of decoding paths in the decoding network according to the keyword, and acquiring a voice recognition text according to the scores of the decoding paths. By utilizing the scheme of the invention, the accuracy of the speech recognition result can be greatly improved.

Description

technical field [0001] The invention relates to the field of voice recognition, in particular to a voice recognition method and device. Background technique [0002] At present, with the development of artificial intelligence technology, machine simultaneous interpretation has appeared. The biggest advantage of machine simultaneous interpretation is that it will not reduce the translation rate due to fatigue. Machine simultaneous interpretation is limited by speech recognition technology and machine translation technology, and the quality of machine translation depends on the quality of speech recognition text. Therefore, in order to improve the accuracy of machine simultaneous interpretation, it is necessary to have a high-quality speech recognition system. In some machine simultaneous interpretation application scenarios, it is often encountered the problem of recognition and translation of substantive words or professional nouns such as names of people, places, and produc...

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
no application Login to view more
IPC IPC(8): G10L15/08G10L15/18G10L15/22G10L15/26G06F16/30
CPCG10L15/08G10L15/18G10L15/22G10L15/26
Inventor 赵超
Owner BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap