Segment Length Matters: A Study of Segment Lengths on Audio Fingerprinting Performance

2026-01-25

AI Summary

This study addresses the longstanding reliance on heuristic approaches in selecting segment lengths for audio fingerprinting systems, a choice that has lacked systematic investigation. For the first time, it quantitatively evaluates the impact of varying segment durations on the retrieval performance of neural audio fingerprinting models. The work proposes an optimization framework that integrates multi-scale segment processing with recommendations from large language models—such as GPT-5-mini—to guide optimal length selection. Experimental results demonstrate that short segments of 0.5 seconds consistently enhance retrieval accuracy across diverse datasets. Furthermore, the large language model proves effective in recommending near-optimal segment lengths across multiple evaluation metrics, offering practical design guidance for scalable audio retrieval systems.

Technology Category

• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Security and Privacy: Large-scale security measurements

Abstract

Audio fingerprinting provides an identifiable representation of acoustic signals, which can be later used for identification and retrieval systems. To obtain a discriminative representation, the input audio is usually segmented into shorter time intervals, allowing local acoustic features to be extracted and analyzed. Modern neural approaches typically operate on short, fixed-duration audio segments, yet the choice of segment duration is often made heuristically and rarely examined in depth. In this paper, we study how segment length affects audio fingerprinting performance. We extend an existing neural fingerprinting architecture to adopt various segment lengths and evaluate retrieval accuracy across different segment lengths and query durations. Our results show that short segment lengths (0.5-second) generally achieve better performance. Moreover, we evaluate LLM capacity in recommending the best segment length, which shows that GPT-5-mini consistently gives the best suggestions across five considerations among three studied LLMs. Our findings provide practical guidance for selecting segment duration in large-scale neural audio retrieval systems.

Problem

• audio fingerprinting
• segment length
• retrieval performance
• neural audio retrieval
• acoustic signal representation

Innovation

• audio fingerprinting
• segment length
• neural retrieval
• large language models
• retrieval accuracy