A Survey of Automatic Evaluation Methods on Text, Visual and Speech Generations

TL;DR

This paper provides a comprehensive review and taxonomy of automatic evaluation methods for generated content across text, visual, and speech modalities, highlighting current approaches and future research directions.

Contribution

It introduces a unified framework and taxonomy for evaluating generated content across multiple modalities, addressing the lack of systematic organization in existing methods.

Findings

Identifies five fundamental evaluation paradigms across modalities.

Extends evaluation framework from text to images and audio.

Discusses promising future directions for cross-modal evaluation.

Abstract

Recent advances in deep learning have significantly enhanced generative AI capabilities across text, images, and audio. However, automatically evaluating the quality of these generated outputs presents ongoing challenges. Although numerous automatic evaluation methods exist, current research lacks a systematic framework that comprehensively organizes these methods across text, visual, and audio modalities. To address this issue, we present a comprehensive review and a unified taxonomy of automatic evaluation methods for generated content across all three modalities; We identify five fundamental paradigms that characterize existing evaluation approaches across these domains. Our analysis begins by examining evaluation methods for text generation, where techniques are most mature. We then extend this framework to image and audio generation, demonstrating its broad applicability. Finally, we discuss promising directions for future research in cross-modal evaluation methodologies.