# Improving Audio Classification by Transitioning from Zero- to Few-Shot

arXiv: https://arxiv.org/abs/2507.20036 · HTML: https://mlsanity.com/paper/2507.20036/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 26 Jul 2025.

## Builds on (most cited first, 15 of 15)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation](https://mlsanity.com/paper/2211.06687/) (2022)
- [FSD50K: An Open Dataset of Human-Labeled Sound Events](https://mlsanity.com/paper/2010.00475/) (2020)
- [AudioCLIP: Extending CLIP to Image, Text and Audio](https://mlsanity.com/paper/2106.13043/) (2021)
- [Pengi: An Audio Language Model for Audio Tasks](https://mlsanity.com/paper/2305.11834/) (2023)
- [Wav2CLIP: Learning Robust Audio Representations From CLIP](https://mlsanity.com/paper/2110.11499/) (2021)
- [Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities](https://mlsanity.com/paper/2402.01831/) (2024)
- [A Review of Feature Selection Methods Based on Mutual Information](https://mlsanity.com/paper/1509.07577/) (2015)
- [Natural Language Supervision for General-Purpose Audio Representations](https://mlsanity.com/paper/2309.05767/) (2023)
- [CochlScene: Acquisition of acoustic scene data using crowdsourcing](https://mlsanity.com/paper/2211.02289/) (2022)
- [Audio-Text Models Do Not Yet Leverage Natural Language](https://mlsanity.com/paper/2303.10667/) (2023)
- [M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation](https://mlsanity.com/paper/2406.02032/) (2024)
- [Learning from Taxonomy: Multi-label Few-Shot Classification for Everyday Sound Recognition](https://mlsanity.com/paper/2212.08952/) (2022)
- [Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation](https://mlsanity.com/paper/2407.19265/) (2024)
- [SECP: A Speech Enhancement-Based Curation Pipeline For Scalable Acquisition Of Clean Speech](https://mlsanity.com/paper/2402.12482/) (2024)

## Built on by (most cited first, 1 of 1)

- [CALM: Class-Conditional Sparse Attention Vectors for Large Audio-Language Models](https://mlsanity.com/paper/2602.07077/) (2026)

## Abstract (arXiv)

State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks trained through contrastive learning to align audio and text representations. Identifying the optimal text description for an audio class is challenging, particularly when the class comprises a wide variety of sounds. This paper examines few-shot methods designed to improve classification accuracy beyond the zero-shot approach. Specifically, audio embeddings are grouped by class and processed to replace the inherently noisy text embeddings. Our results demonstrate that few-shot classification typically outperforms the zero-shot baseline.