# Multi-level Fusion of Wav2vec 2.0 and BERT for Multimodal Emotion Recognition

arXiv: https://arxiv.org/abs/2207.04697 · HTML: https://mlsanity.com/paper/2207.04697/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 36 references that are in the map.
- First posted on arXiv 11 Jul 2022.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2010.10504/) (2020)
- [Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory](https://mlsanity.com/paper/1704.01074/) (2017)
- [Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings](https://mlsanity.com/paper/2104.03502/) (2021)
- [Exploring wav2vec 2.0 on speaker verification and language identification](https://mlsanity.com/paper/2012.06185/) (2020)
- [Leveraging BERT for Extractive Text Summarization on Lectures](https://mlsanity.com/paper/1906.04165/) (2019)
- [Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis](https://mlsanity.com/paper/2107.13669/) (2021)
- [Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition](https://mlsanity.com/paper/2008.06682/) (2020)
- [Multimodal Emotion Recognition with High-level Speech and Text Features](https://mlsanity.com/paper/2111.10202/) (2021)
- [Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds](https://mlsanity.com/paper/1911.02365/) (2019)
- [Group Gated Fusion on Attention-based Bidirectional Alignment for Multimodal Emotion Recognition](https://mlsanity.com/paper/2201.06309/) (2022)

## Built on by (most cited first, 9 of 9)

- [LibriSQA: A Novel Dataset and Framework for Spoken Question Answering with Large Language Models](https://mlsanity.com/paper/2308.10390/) (2023)
- [GEmo-CLAP: Gender-Attribute-Enhanced Contrastive Language-Audio Pretraining for Accurate Speech Emotion Recognition](https://mlsanity.com/paper/2306.07848/) (2023)
- [Using Auxiliary Tasks In Multimodal Fusion Of Wav2vec 2.0 And BERT For Multimodal Emotion Recognition](https://mlsanity.com/paper/2302.13661/) (2023)
- [Knowledge-aware Bayesian Co-attention for Multimodal Emotion Recognition](https://mlsanity.com/paper/2302.09856/) (2023)
- [Multilevel Transformer For Multimodal Emotion Recognition](https://mlsanity.com/paper/2211.07711/) (2022)
- [Multimodal Belief Prediction](https://mlsanity.com/paper/2406.07466/) (2024)
- [Retrieval-Augmented Personalization with Foundation Models for Wearable Stress Detection](https://mlsanity.com/paper/2606.24985/) (2026)
- [Efficient infusion of self-supervised representations in Automatic Speech Recognition](https://mlsanity.com/paper/2404.12628/) (2024)
- [When Does Quality-Aware Multimodal Fusion Matter? A Leakage-Safe Diagnostic for Decision-Level Dependence](https://mlsanity.com/paper/2606.26473/) (2026)

## Abstract (arXiv)

The research and applications of multimodal emotion recognition have become increasingly popular recently. However, multimodal emotion recognition faces the challenge of lack of data. To solve this problem, we propose to use transfer learning which leverages state-of-the-art pre-trained models including wav2vec 2.0 and BERT for this task. Multi-level fusion approaches including coattention-based early fusion and late fusion with the models trained on both embeddings are explored. Also, a multi-granularity framework which extracts not only frame-level speech embeddings but also segment-level embeddings including phone, syllable and word-level speech embeddings is proposed to further boost the performance. By combining our coattention-based early fusion model and late fusion model with the multi-granularity feature extraction framework, we obtain result that outperforms best baseline approaches by 1.3% unweighted accuracy (UA) on the IEMOCAP dataset.