Session emotion autoanalysis method based on depth learning

Abstract

The invention discloses a session emotion autoanalysis method based on depth learning and belongs to the natural language processing and data mining field. According to the method, voice and text expression is learned on the basis of a de-noising auto-encoder, further through a depth learning method, depth fusion of two types of expressions is realized to acquire unified high level expression, and emotion analysis is carried out on the basis of high level expression after fusion. Through the method, depth fusion of acoustic and text characteristics is realized, and emotion classification accuracy is improved.

Description

technical field [0001] The invention belongs to the fields of natural language processing and data mining, and in particular relates to an emotion analysis method in voice conversation based on deep learning. Background technique [0002] Sentiment analysis of voice conversation is to judge the emotional state of the speaker, such as happiness, satisfaction, anger, etc., by analyzing the words. Voice conversations exist in a large number of practical fields, including various call centers, human-computer interaction systems, etc. Automatic conversational sentiment analysis helps to dynamically understand the psychological state and emotional changes of the conversationalist, and has broad application prospects. Taking the call center as an example, by analyzing the emotions and emotional changes of the conversationalists during the customer service dialogue, the managers can find out whether the waiter’s attitude is friendly and whether the customer is dissatisfied during t...

AI Technical Summary

Problems solved by technology

However, the low-level representation of acoustic features and text features is usually a nonlinear relationship, and this direct combination is difficult to capture the association between the two features, and the dimension after the combination may be very large

Images