Research

Paper

AI LLM March 24, 2026

Prompt Amplification and Zero-Shot Late Fusion in Audio-Language Models for Speech Emotion Recognition

Authors

Saurabh Kataria, Xiao Hu

Abstract

Audio-Language Models (ALMs) are making strides in understanding speech and non-speech audio. However, domain-specialist Foundation Models (FMs) remain the best for closed-ended speech processing tasks such as Speech Emotion Recognition (SER). Using ALMs for Zero-shot SER is a popular choice, but their potential to work with specialists to achieve state-of-the-art (SOTA) performance remains unexplored. We propose ZS-Fuse, a late-fusion method that combines zero-shot emotion estimates from a dual-encoder ALM with specialist FMs. To handle ambiguity in emotions and sensitivity to prompt choice, 1) we use a simple prompt ensemble and 2) suggest a novel technique called prompt amplification, which repeats audio and text queries to discover stronger zero-shot capabilities. We demonstrate the efficacy of our technique by evaluating ZS-Fuse with three dual-encoder ALMs and two FMs, and report improvements over SOTA baselines, such as WavLM-Large, on three speech emotion recognition datasets.

Metadata

arXiv ID: 2603.23057
Provider: ARXIV
Primary Category: eess.AS
Published: 2026-03-24
Fetched: 2026-03-25 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.23057v1</id>\n    <title>Prompt Amplification and Zero-Shot Late Fusion in Audio-Language Models for Speech Emotion Recognition</title>\n    <updated>2026-03-24T10:55:55Z</updated>\n    <link href='https://arxiv.org/abs/2603.23057v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.23057v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Audio-Language Models (ALMs) are making strides in understanding speech and non-speech audio. However, domain-specialist Foundation Models (FMs) remain the best for closed-ended speech processing tasks such as Speech Emotion Recognition (SER). Using ALMs for Zero-shot SER is a popular choice, but their potential to work with specialists to achieve state-of-the-art (SOTA) performance remains unexplored. We propose ZS-Fuse, a late-fusion method that combines zero-shot emotion estimates from a dual-encoder ALM with specialist FMs. To handle ambiguity in emotions and sensitivity to prompt choice, 1) we use a simple prompt ensemble and 2) suggest a novel technique called prompt amplification, which repeats audio and text queries to discover stronger zero-shot capabilities. We demonstrate the efficacy of our technique by evaluating ZS-Fuse with three dual-encoder ALMs and two FMs, and report improvements over SOTA baselines, such as WavLM-Large, on three speech emotion recognition datasets.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.AS'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <published>2026-03-24T10:55:55Z</published>\n    <arxiv:primary_category term='eess.AS'/>\n    <author>\n      <name>Saurabh Kataria</name>\n    </author>\n    <author>\n      <name>Xiao Hu</name>\n    </author>\n  </entry>"
}