Can We Estimate Purchase Intention Based on Zero-shot Speech Emotion Recognition?

TL;DR

This paper introduces a zero-shot speech emotion recognition method that estimates unknown bipolar emotions like purchase intention directly from speech, expanding the CLAP framework with multi-class and multi-task settings.

Contribution

It presents the first approach to estimate purchase intention from speech in a zero-shot manner, extending existing frameworks to recognize unknown bipolar emotions.

Findings

Zero-shot estimation performance matches supervised models.

The method effectively recognizes unknown bipolar emotions.

First attempt to directly estimate purchase intention from speech.

Abstract

This paper proposes a zero-shot speech emotion recognition (SER) method that estimates emotions not previously defined in the SER model training. Conventional methods are limited to recognizing emotions defined by a single word. Moreover, we have the motivation to recognize unknown bipolar emotions such as ``I want to buy - I do not want to buy.'' In order to allow the model to define classes using sentences freely and to estimate unknown bipolar emotions, our proposed method expands upon the contrastive language-audio pre-training (CLAP) framework by introducing multi-class and multi-task settings. We also focus on purchase intention as a bipolar emotion and investigate the model's performance to zero-shot estimate it. This study is the first attempt to estimate purchase intention from speech directly. Experiments confirm that the results of zero-shot estimation by the proposed method are at the same level as those of the model trained by supervised learning.