Emotion recognition in speech chatbot job interview system

摘要

Methods and systems are provided for speech emotion recognition interview process. In one novel aspect, in addition to contents assessment to an answer audio clip, the concurrent sentiment classifier is generated based on emotion classifier of the answer audio clip. In one embodiment, the computer system obtains a sentiment classifier of an audio clip of a first answer to the first question, wherein the sentiment classifier is derived from an emotion classifier resulting from a convolutional neural network (CNN) model analysis of the audio clip; obtains an assessment result to the first question by analyzing the audio clip of the first answer to the first question using a recurrent neural network (RNN) model; and generates a first emotion response result to the first question based on the sentiment classifier and the assessment result, wherein the first emotion response result presents a sampling experience factor to the response assessment result.