用单次神经前向传播实现音乐识别，比传统方法更快更省存储。
Turning music identification into a neural forward pass
- 用生成式Transformer直接从音频片段预测曲目标识，跳过传统检索流程。
- 1秒音频识别准确率超当前最佳，存储仅需基线的0.33%，延迟降低2.3倍。
- 可识别未见过的歌曲并拒绝错误匹配，适合开放环境下的实时音乐识别。
搜索是计算机科学中的基础操作，通常采用规则驱动的系统2式流程：计算键值、查询索引、验证候选。而人类识别则类似系统1的关联式记忆，部分线索即可触发回忆，无需显式枚举、排序或访问离散候选。本文展示，通过在音频数据集上训练的生成式Transformer，音乐声音识别这一复杂搜索任务可在一次神经前向传播中完成。模型从短音频片段预测对应曲目标识，性能超越当前最优声学指纹技术，尤其在1秒短片段上提升显著。该方法将外部存储需求降至基线的0.33%，推理延迟（p95）降低2.3倍。此外，模型能拒绝未见曲目查询，支持开放集运行，降低误标风险。以音乐曲目识别为例，本工作重构了搜索范式，使其更贴近人类的联想式识别，而非算法化数据库查找。
原文摘要 · Abstract (English)
Search, a foundational operation in computer science, maps a query to a matching item in a collection. It is typically implemented as a System-2 like, rule-based pipeline in which a key is computed, an index is probed, and candidates are verified. By contrast, human recognition resembles a System-1 like, associative model of identity recovery, in which even partial cues can trigger a recall without explicitly enumerating, ranking, or even accessing discrete candidates. Here, we show that music sound identification, a difficult search problem, can be performed in a single neural feed-forward pass by a generative transformer. Trained on an audio dataset, the model predicts the corresponding track identifier from a short audio excerpt. This approach surpasses state-of-the-art acoustic fingerprinting, with the largest gains for short audio segments (1 second), demonstrating the method is not only viable but advantageous. Moreover, it reduces external storage to 0.33% of the baseline footprint and improves inference latency by 2.3x (p95). Furthermore, the model can reject queries for unseen tracks, supporting open-set operation while reducing misattribution risk. Using music track identification as an example, this work reframes search, bringing it closer in spirit to human associative recognition and away from algorithmic database lookup.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。