Human-computer interactive speech recognition method and system used for intelligent equipment

Abstract

The invention discloses a human-computer interactive speech recognition method and system used for intelligent equipment, and belongs to the technical field of speech recognition. The accuracy of speech recognition is improved through joint optimization training of intention recognition and slot filling. The method includes the following steps that user's voice problem word segmentation is processed to obtain an original word sequence, and the original word sequence is vectorized through embedding processing; a slot label model yiS is obtained by weighting an implicit state vector hi and a slot context vector ciS; an intention anticipation model yI is obtained by weighting an implicit state vector hT and an intent context vector ciS; a slot door g is used for splicing the slot context vector ciS and the intent context vector ciS, and a slot gate g is used for converting the slot label model yiS; a target function is constructed through joint optimization of the intention anticipation model yI and the slot label model yiS obtained after conversion, and the user's voice problem is subjected to intention recognition based on the target function.

Description

technical field [0001] The present invention relates to the technical field of voice recognition, in particular to a human-computer interaction voice recognition method and system for smart devices. Background technique [0002] With the development of Internet technology, there are more and more smart devices using voice for human-computer interaction. The existing voice interaction systems include Siri, Xiaomi, Cortana, Xiaoice, Dumi, etc. Compared with traditional In terms of manual input human-computer interaction, it is convenient and efficient, and has a wide range of application scenarios. In the process of speech recognition, intent recognition and slot filling technology are the keys to ensure the accuracy of speech recognition results. [0003] For intent recognition, it can be abstracted as a classification problem, and then the CNN+knowledge representation classifier is used to train the intent recognition model. In the intent recognition model, in addition to wo...

AI Technical Summary

Problems solved by technology

[0003] For intent recognition, it can be abstracted as a classification problem, and then the CNN+knowledge representation classifier is used to train the intent recognition model. In the intent recognition model, in addition to word embedding of the user's voice problem, the semantics of knowledge are also introduced. representation to increase the generalization ability of the presentation layer, but in practical applications, it is found that the model has the defect of slot information filling bias, which affects the accuracy of the intent recognition model

For slot filling, the essence is to formalize the sentence sequence into a label sequence. There are many commonly used methods for labeling sequences, such as hidden Markov models or conditional random field models, but these slot filling models are not suitable for specific applications. In the scene, due to the lack of context information, there will be ambiguity in slots under different semantic intentions, which cannot meet the actual application requirements

It can be seen that the training of the two models in the prior art is carried out independently, and there is no combined optimization for the intent recognition task and the slot filling task, which eventually leads to the problem of low recognition accuracy of the trained model in terms of speech recognition, reducing the user experience

Images