# Finding Emotions Where They Belong: Rethinking Audio Emotion Recognition through Masked Temporal Affective Grounding

arXiv: https://arxiv.org/abs/2609.32804 · HTML: https://mlsanity.com/paper/2609.32804/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 29 references that are in the map.
- First posted on arXiv 26 Sep 2026.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [Qwen2-Audio Technical Report](https://mlsanity.com/paper/2407.10759/) (2024)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [Audio-Reasoner: Improving Reasoning Capability in Large Audio Language Models](https://mlsanity.com/paper/2503.02318/) (2025)
- [The Emotional Voices Database: Towards Controlling the Emotion Dimension in Voice Generation Systems](https://mlsanity.com/paper/1806.09514/) (2018)
- [HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding](https://mlsanity.com/paper/2501.15111/) (2025)
- [AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models](https://mlsanity.com/paper/2501.16566/) (2025)
- [rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method](https://mlsanity.com/paper/1906.03588/) (2019)
- [SECap: Speech Emotion Captioning with Large Language Model](https://mlsanity.com/paper/2312.10381/) (2023)
- [Beyond Silent Letters: Amplifying LLMs in Emotion Recognition with Vocal Nuances](https://mlsanity.com/paper/2407.21315/) (2024)
- [Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music](https://mlsanity.com/paper/2604.10905/) (2026)
- [MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models](https://mlsanity.com/paper/2508.09210/) (2025)
- [AffectGPT-R1: Leveraging Reinforcement Learning for Open-Vocabulary Multimodal Emotion Recognition](https://mlsanity.com/paper/2508.01318/) (2025)
- [Speech Emotion Diarization: Which Emotion Appears When?](https://mlsanity.com/paper/2306.12991/) (2023)
- [Emotion-Coherent Reasoning for Multimodal LLMs via Emotional Rationale Verifier](https://mlsanity.com/paper/2510.23506/) (2025)
- [VowelPrompt: Hearing Speech Emotions from Text via Vowel-level Prosodic Augmentation](https://mlsanity.com/paper/2602.06270/) (2026)
- [TAC: Timestamped Audio Captioning](https://mlsanity.com/paper/2602.15766/) (2026)
- [The Devil is in the EOS: Sequence Training for Detailed Image Captioning](https://mlsanity.com/paper/2507.20077/) (2025)

## Abstract (arXiv)

Audio emotion recognition (AER) typically assigns a single label to an entire recording, leaving the temporal scope of that label ambiguous when multiple speakers and affective events are present. We address this limitation by reformulating AER as a Temporal Affective Grounding (TAG) task that associates emotions with temporally bounded speech spans and vocal tone descriptions. To support this formulation, we curate temporally annotated versions of existing emotion recognition datasets and construct recordings containing two to four affective speech spans, including overlapping speech. Training in this longer format with a standard language-modeling objective can degrade both emotion recognition and temporal grounding performance, while tone descriptions can provide shortcuts for emotion prediction. To address these challenges, we introduce Masked Temporal Affective Grounding (M-TAG), a supervised training objective that combines full-sequence language modeling with emotion and timestamp cross-entropy losses under attention masking. The masking varies the context visible to emotion-label tokens to reduce reliance on shortcuts and improve generalization, while the timestamp loss incorporates a distance-aware weight to penalize larger temporal errors. We evaluate EMO-TAG, a model fine-tuned using our dataset and objective, on emotion recognition and affective temporal-grounding against three AER and audio-language baselines: Flamingo-Next, Audio-Reasoner, and AffectGPT. Our results show that existing models achieve limited affective temporal-grounding despite competitive emotion recognition performance.