Speech recognition text processing method and system
A speech recognition and text processing technology, applied in speech recognition, speech analysis, instruments, etc., can solve the problems of misleading users, user interference, low intelligibility of recognized text, etc., to improve efficiency and accuracy, reduce misleading, and facilitate selected effect
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Publication Date
- 2019-10-18
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the technical field of speech signal processing, in particular to a text processing method and system for speech recognition. Background technique
[0002] With the development of speech technology, automatic speech recognition technology has been widely used in various fields of production and life, and various practical speech recognition systems have been constructed, such as speech conference transcription systems. However, in actual recognition texts, there are often recognition texts of various abnormal speech data, so some abnormal recognition texts will inevitably be generated. Due to the low intelligibility of the recognition text of abnormal voice data, users often cannot understand the semantics expressed in the recognition text, causing interference to users, and even misleading users. , recognize the text as "Nine hundred and ninety-nine can go". Therefore, how to reduce the interference of abnormal speech recogn...
Examples
Embodiment Construction
[0079] 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.
[0080] Embodiments of the present invention provide a voice recognition text processing method and system, which automatically detects abnormal voices in the voice data according to the voice recognition results, detects the abnormal voices in the voice data, and then performs the corresponding abnormal voice in the obtained recognition text. Marking, providing the marked recognition text to the user, so as to achieve the function of prompting the user and reduce the misleading of the abnormal text to the user.
[0081] Such as figure 1 Shown is the flowchart of the voice recognition text processing method of the embodiment of the present invention, comprising the following steps:
[0082] Step 101, acquire voi...