# Acoustic Cue Alignment in Audio Language Models for Speech Emotion Recognition

arXiv: https://arxiv.org/abs/2606.07309 · HTML: https://mlsanity.com/paper/2606.07309/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 42 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 30 of 33)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [Attention is not Explanation](https://mlsanity.com/paper/1902.10186/) (2019)
- [Training Large Language Models to Reason in a Continuous Latent Space](https://mlsanity.com/paper/2412.06769/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?](https://mlsanity.com/paper/2004.03685/) (2020)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Pengi: An Audio Language Model for Audio Tasks](https://mlsanity.com/paper/2305.11834/) (2023)
- [AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension](https://mlsanity.com/paper/2402.07729/) (2024)
- [Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models](https://mlsanity.com/paper/2507.08128/) (2025)
- [Dawn of the transformer era in speech emotion recognition: closing the valence gap](https://mlsanity.com/paper/2203.07378/) (2022)
- [AudioBench: A Universal Benchmark for Audio Large Language Models](https://mlsanity.com/paper/2406.16020/) (2024)
- [Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models](https://mlsanity.com/paper/2503.02318/) (2025)
- [A Survey on Speech Large Language Models for Understanding](https://mlsanity.com/paper/2410.18908/) (2024)
- [SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information](https://mlsanity.com/paper/2505.13237/) (2025)
- [Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models](https://mlsanity.com/paper/2406.08402/) (2024)
- [Frozen Large Language Models Can Perceive Paralinguistic Aspects of Speech](https://mlsanity.com/paper/2410.01162/) (2024)
- [VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models](https://mlsanity.com/paper/2505.15727/) (2025)
- [Incentivizing Consistent, Effective and Scalable Reasoning Capability in Audio LLMs via Reasoning Process Rewards](https://mlsanity.com/paper/2510.20867/) (2025)
- [Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples](https://mlsanity.com/paper/2505.14518/) (2025)
- [ParaCLAP -- Towards a general language-audio model for computational paralinguistic tasks](https://mlsanity.com/paper/2406.07203/) (2024)
- [Benchmarking and Confidence Evaluation of LALMs For Temporal Reasoning](https://mlsanity.com/paper/2505.13115/) (2025)
- [Computer Audition: From Task-Specific Machine Learning to Foundation Models](https://mlsanity.com/paper/2407.15672/) (2024)
- [Affective Computing Has Changed: The Foundation Model Disruption](https://mlsanity.com/paper/2409.08907/) (2024)
- [Designing and Evaluating Speech Emotion Recognition Systems: A reality check case study with IEMOCAP](https://mlsanity.com/paper/2304.00860/) (2023)
- [Discovering and Causally Validating Emotion-Sensitive Neurons in Large Audio-Language Models](https://mlsanity.com/paper/2601.03115/) (2026)
- [Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning](https://mlsanity.com/paper/2602.11909/) (2026)

## Abstract (arXiv)

Instruction-following audio language models (ALMs) can be augmented with explicit acoustic cues, yet it remains unclear whether such cues are used in a grounded way when the raw audio is already available. We study this question in speech emotion recognition (SER) by deriving six interpretable acoustic concept tokens from the standardised eGeMAPS paralinguistic feature set. These tokens summarise energy, pitch, dynamics, brightness, formants, and voice quality, and are appended to the textual prompt while the audio input is kept unchanged. Across the widely used FAU-Aibo and IEMOCAP benchmarks, aligned tokens improve unweighted average recall (UAR), whereas shuffled, conflicting, or corrupted tokens reduce performance relative to aligned tokens and shift confusions toward neutral. Importantly, predictions do not collapse under strong token perturbations, suggesting that the models are sensitive to the symbolic cue channel but remain partly anchored to the audio signal. We argue that token-only interventions provide a practical way to probe audio-grounded cue use, robustness, and interpretability in ALM-based affective computing.