@inproceedings{seth-etal-2025-pat,
title = "{PAT}: Parameter-Free Audio-Text Aligner to Boost Zero-Shot Audio Classification",
author = "Seth, Ashish and
Selvakumar, Ramaneswaran and
Kumar, Sonal and
Ghosh, Sreyan and
Manocha, Dinesh",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.616/",
doi = "10.18653/v1/2025.naacl-long.616",
pages = "12376--12394",
ISBN = "979-8-89176-189-6",
abstract = "Audio-Language Models (ALMs) have demonstrated remarkable performance in zero-shot audio classification. In this paper, we introduce PAT (Parameter-free Audio-Text aligner), a simple and training-free method aimed at boosting zero-shot audio classification performance of CLAP-like ALMs. To achieve this, we propose to improve the cross-modal interaction between audio and language modalities by enhancing the representations for both modalities using mutual feedback. Precisely, to enhance textual representations, we propose a prompt ensemble algorithm that automatically selects and combines the most relevant prompts from a datastore with a large pool of handcrafted prompts and weighs them according to their relevance to the audio. On the other hand, to enhance audio representations, we reweigh the frame-level audio features based on the enhanced textual information. Our proposed method does not require any additional modules or parameters and can be used with any existing CLAP-like ALM to improve zero-shot audio classification performance. We experiment across 18 diverse benchmark datasets and 6 ALMs and show that the PAT outperforms vanilla zero-shot evaluation with significant margins of 0.42{\%}-27.0{\%}. Additionally, we demonstrate that PAT maintains robust performance even when input audio is degraded by varying levels of noise. We make our code publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seth-etal-2025-pat">
<titleInfo>
<title>PAT: Parameter-Free Audio-Text Aligner to Boost Zero-Shot Audio Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ashish</namePart>
<namePart type="family">Seth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramaneswaran</namePart>
<namePart type="family">Selvakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sonal</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sreyan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinesh</namePart>
<namePart type="family">Manocha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Audio-Language Models (ALMs) have demonstrated remarkable performance in zero-shot audio classification. In this paper, we introduce PAT (Parameter-free Audio-Text aligner), a simple and training-free method aimed at boosting zero-shot audio classification performance of CLAP-like ALMs. To achieve this, we propose to improve the cross-modal interaction between audio and language modalities by enhancing the representations for both modalities using mutual feedback. Precisely, to enhance textual representations, we propose a prompt ensemble algorithm that automatically selects and combines the most relevant prompts from a datastore with a large pool of handcrafted prompts and weighs them according to their relevance to the audio. On the other hand, to enhance audio representations, we reweigh the frame-level audio features based on the enhanced textual information. Our proposed method does not require any additional modules or parameters and can be used with any existing CLAP-like ALM to improve zero-shot audio classification performance. We experiment across 18 diverse benchmark datasets and 6 ALMs and show that the PAT outperforms vanilla zero-shot evaluation with significant margins of 0.42%-27.0%. Additionally, we demonstrate that PAT maintains robust performance even when input audio is degraded by varying levels of noise. We make our code publicly available.</abstract>
<identifier type="citekey">seth-etal-2025-pat</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.616</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.616/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>12376</start>
<end>12394</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PAT: Parameter-Free Audio-Text Aligner to Boost Zero-Shot Audio Classification
%A Seth, Ashish
%A Selvakumar, Ramaneswaran
%A Kumar, Sonal
%A Ghosh, Sreyan
%A Manocha, Dinesh
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F seth-etal-2025-pat
%X Audio-Language Models (ALMs) have demonstrated remarkable performance in zero-shot audio classification. In this paper, we introduce PAT (Parameter-free Audio-Text aligner), a simple and training-free method aimed at boosting zero-shot audio classification performance of CLAP-like ALMs. To achieve this, we propose to improve the cross-modal interaction between audio and language modalities by enhancing the representations for both modalities using mutual feedback. Precisely, to enhance textual representations, we propose a prompt ensemble algorithm that automatically selects and combines the most relevant prompts from a datastore with a large pool of handcrafted prompts and weighs them according to their relevance to the audio. On the other hand, to enhance audio representations, we reweigh the frame-level audio features based on the enhanced textual information. Our proposed method does not require any additional modules or parameters and can be used with any existing CLAP-like ALM to improve zero-shot audio classification performance. We experiment across 18 diverse benchmark datasets and 6 ALMs and show that the PAT outperforms vanilla zero-shot evaluation with significant margins of 0.42%-27.0%. Additionally, we demonstrate that PAT maintains robust performance even when input audio is degraded by varying levels of noise. We make our code publicly available.
%R 10.18653/v1/2025.naacl-long.616
%U https://aclanthology.org/2025.naacl-long.616/
%U https://doi.org/10.18653/v1/2025.naacl-long.616
%P 12376-12394
Markdown (Informal)
[PAT: Parameter-Free Audio-Text Aligner to Boost Zero-Shot Audio Classification](https://aclanthology.org/2025.naacl-long.616/) (Seth et al., NAACL 2025)
ACL
- Ashish Seth, Ramaneswaran Selvakumar, Sonal Kumar, Sreyan Ghosh, and Dinesh Manocha. 2025. PAT: Parameter-Free Audio-Text Aligner to Boost Zero-Shot Audio Classification. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 12376–12394, Albuquerque, New Mexico. Association for Computational Linguistics.