Semantic comprehension model training method and device, semantic processing method and device and storage medium

Abstract

The invention provides a semantic comprehension model training method, which comprises the steps of obtaining a first training sample set, and performing denoising processing on the first training sample set to form a corresponding second training sample set; processing the second training sample set through a semantic comprehension model to determine initial parameters of the semantic comprehension model; responding to the initial parameters of the semantic comprehension model, processing the second training sample set through the semantic comprehension model, and determining updating parameters of the semantic comprehension model; and according to the update parameters of the semantic comprehension model, performing iterative update on the semantic representation layer network parametersand the task-related output layer network parameters of the semantic comprehension model through the second training sample set. The invention further provides a semantic comprehension model processing method and device and a storage medium. According to the method, the training precision and the training speed of the semantic comprehension model can be improved, so that the semantic comprehension model can adapt to different use scenes, and the influence of environmental noise on the semantic comprehension model is avoided.

Description

technical field [0001] The invention relates to machine learning technology, in particular to a training method for a semantic understanding model, a semantic processing method, a device and a storage medium. Background technique [0002] In the usage scenario of full-duplex voice interaction, it is necessary to implement the following operations in a multi-sound source environment where multiple sound sources continuously emit sound at the same time: for example, the recognition of voice identities (male, female, and child), triggering dialogues with different contents, voice Emotion recognition, music / singing recognition, etc.; environmental processing, background noise recognition and echo cancellation, in this process, the semantic understanding model has nothing to do with the field of background noise and other people's chatting in the full-duplex dialogue scene (OOD, Out -Of-Domain) corpus is easier to be listened to by assistants. If such corpus is misresponsed by sm...

AI Technical Summary

Problems solved by technology

[0002] In the usage scenario of full-duplex voice interaction, it is necessary to implement the following operations in a multi-sound source environment where multiple sound sources continuously emit sound at the same time: for example, the recognition of voice identities (male, female, and child), triggering dialogues with different contents, voice Emotion recognition, music / singing recognition, etc.; environmental processing, background noise recognition and echo cancellation, in this process, the semantic understanding model has nothing to do with the field of background noise and other people's chatting in the full-duplex dialogue scene (OOD, Out -Of-Domain) corpus is easier to be listened to by assistants. If such corpus is misresponsed by smart assistants, the interaction success rate is low and affects the user experience

Images