Punctuation adding method and device and device for adding punctuations

Abstract

The embodiments of the invention provide a punctuation adding method and device and a device for adding punctuations. The method specifically comprises the steps of: acquiring a text to be processed; and adding punctuations for the text to be processed via a neural network conversion model to obtain a punctuation adding result corresponding to the text to be processed, wherein the neural network conversion model is obtained by training parallel corpuses, the parallel corpuses comprise a source corpus and a destination corpus, and the destination corpus comprise punctuations corresponding to words in the source corpus. The punctuation adding method and device can improve the punctuation adding accuracy.

Description

technical field [0001] The invention relates to the technical field of information processing, in particular to a method and device for adding punctuation, and a device for adding punctuation. Background technique [0002] In the field of information processing technology such as the communication field and the Internet field, in some application scenarios, it is necessary to add punctuation to some files lacking punctuation. For example, for the convenience of reading, punctuation and the like are added to the text corresponding to the speech recognition result. [0003] In the existing solution, punctuation can be added to the text corresponding to the speech recognition result according to the silence interval of the speech signal. Specifically, the threshold of the length of silence can be set at first, if the length of the silence interval when the speaking user speaks in the voice signal exceeds the threshold, then punctuation is added at the corresponding position; ...

AI Technical Summary

Problems solved by technology

[0004] However, the inventor found in the process of implementing the embodiment of the present invention that different speaking users often have different speech rates. In this way, adding punctuation to the text corresponding to the speech recognition result according to the silence interval of the speech signal in the existing solution will affect Accuracy of punctuation

For example, if the speaking user's speaking speed is too fast, there is no interval between sentences, or the interval is so short that it is less than the threshold, then no punctuation will be added to the text; In the case of one word, the text will have a lot of punctuation; the above two cases will cause punctuation errors, that is, the accuracy of punctuation is low

Images