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

CN106373558BActive Publication Date: 2019-10-18IFLYTEK CO LTD
5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Publication Date
2019-10-18

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a speech recognition text processing method and a speech recognition text processing system. The method comprises the following steps: acquiring to-be-recognized speech data; conducting speech recognition on the speech data so as to obtain a speech recognition result corresponding to the speech data, wherein the speech recognition result is a recognition text corresponding to the speech data; conducting abnormal speech detection on the speech data so as to determine abnormal speech in the speech data; marking a part, corresponding to the abnormal speech, in the recognition speech; and providing the marked recognition text to a user. With the application of the processing method and the processing system disclosed by the invention, the recognition text of the abnormal speech data can be automatically detected and marked out so as to prompt the user; therefore, misleading to the user is reduced.
Need to check novelty before this filing date? Find Prior Art

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...