Automatic rhythm extracting method, system and application thereof in natural language processing

Abstract

The invention relates to an automatic rhythm extracting method, a system and an application thereof in natural language processing; the method includes steps of applying an automatic text-voice alignment technology to generate a large-scale rhythm data set, and applying a circular neural network to perform modeling on the rhythm of a sentence, adding a bidirectional expanding mechanism; applying the automatically structured text rhythm data to a natural language processing task based on the circular neural network. The method fully uses the isomorphism properties of common sequence data in the text rhythm sequence and the natural language processing task; through an alternative training method under the multi-task study, the natural language processing task is promoted without the assistance of artificially explicit marked semantic information. The practice of the method can overcome shortcomings of low efficiency, different standards, incapability of large-scale application of the artificial rhythm marking; meanwhile, the method can transfer semantics and pragmatics in massive voice data to the other tasks.

Description

technical field [0001] The present invention relates to a speech prosody extraction method, and more specifically, to an automatic prosody extraction method, system and application in natural language processing tasks. Background technique [0002] Prosody in speech can reflect the speaker's intention by giving different prominence to different words in the sentence. Therefore, prosody prosody is considered to have an indicative effect on understanding the semantics and pragmatics of speech. The prosody of speech mainly includes Reading, meaning group pauses, rereading, rising and falling tones and other information. In addition to speech, text is another form that can express semantics and pragmatics, and its inherent prosodic characteristics can be understood and learned by different readers, that is, the text contains its own prosodic characteristics, which is This feature can be learned and predicted, and this inherent prosody can provide semantic and pragmatic guidance...

AI Technical Summary

Problems solved by technology

[0014] For this reason, the object of the present invention is to propose an efficient automatic prosody extraction and its application method on natural language processing tasks, which can overcome the inefficiency, different standards and inability to be applied on a large scale in traditional manual labeling. defects, and can transfer the semantic and pragmatic features existing in a large amount of speech data to other tasks. As a kind of unsupervised data generation method on labeling, the present invention can effectively use the prosodic pattern in the speech, for other tasks Performance improvements for natural language processing tasks

Images