Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition

• URL: http://arxiv.org/abs/2008.06682v1
• Date: Sat, 15 Aug 2020 08:54:48 GMT
• Title: Jointly Fine-Tuning "BERT-like" Self Supervised Models to Improve Multimodal Speech Emotion Recognition
• Authors: Shamane Siriwardhana, Andrew Reis, Rivindu Weerasekera, Suranga Nanayakkara
• Abstract summary: We show that jointly fine-tuning "BERT-like" SSL architectures achieve state-of-the-art (SOTA) results. We also evaluate two methods of fusing speech and text modalities and show that a simple fusion mechanism can outperform more complex ones.
• Score: 9.099532309489996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task. In this paper, we explore the use of modality-specific "BERT-like" pretrained Self Supervised Learning (SSL) architectures to represent both speech and text modalities for the task of multimodal speech emotion recognition. By conducting experiments on three publicly available datasets (IEMOCAP, CMU-MOSEI, and CMU-MOSI), we show that jointly fine-tuning "BERT-like" SSL architectures achieve state-of-the-art (SOTA) results. We also evaluate two methods of fusing speech and text modalities and show that a simple fusion mechanism can outperform more complex ones when using SSL models that have similar architectural properties to BERT.

Related papers

• MM-TTS: A Unified Framework for Multimodal, Prompt-Induced Emotional Text-to-Speech Synthesis [70.06396781553191]
  Multimodal Emotional Text-to-Speech System (MM-TTS) is a unified framework that leverages emotional cues from multiple modalities to generate highly expressive and emotionally resonant speech. MM-TTS consists of two key components: the Emotion Prompt Alignment Module (EP-Align), which employs contrastive learning to align emotional features across text, audio, and visual modalities, and the Emotion Embedding-Induced TTS (EMI-TTS), which integrates the aligned emotional embeddings with state-of-the-art TTS models to synthesize speech that accurately reflects the intended emotions.
  arXiv  Detail & Related papers  (2024-04-29T03:19:39Z)
• AIMDiT: Modality Augmentation and Interaction via Multimodal Dimension Transformation for Emotion Recognition in Conversations [57.99479708224221]
  We propose a novel framework called AIMDiT to solve the problem of multimodal fusion of deep features. Experiments conducted using our AIMDiT framework on the public benchmark dataset MELD reveal 2.34% and 2.87% improvements in terms of the Acc-7 and w-F1 metrics.
  arXiv  Detail & Related papers  (2024-04-12T11:31:18Z)
• Adversarial Representation with Intra-Modal and Inter-Modal Graph Contrastive Learning for Multimodal Emotion Recognition [14.639340916340801]
  We propose a novel Adversarial Representation with Intra-Modal and Inter-Modal Graph Contrastive for Multimodal Emotion Recognition (AR-IIGCN) method. Firstly, we input video, audio, and text features into a multi-layer perceptron (MLP) to map them into separate feature spaces. Secondly, we build a generator and a discriminator for the three modal features through adversarial representation. Thirdly, we introduce contrastive graph representation learning to capture intra-modal and inter-modal complementary semantic information.
  arXiv  Detail & Related papers  (2023-12-28T01:57:26Z)
• UniDiff: Advancing Vision-Language Models with Generative and Discriminative Learning [86.91893533388628]
  This paper presents UniDiff, a unified multi-modal model that integrates image-text contrastive learning (ITC), text-conditioned image synthesis learning (IS), and reciprocal semantic consistency modeling (RSC) UniDiff demonstrates versatility in both multi-modal understanding and generative tasks.
  arXiv  Detail & Related papers  (2023-06-01T15:39:38Z)
• HCAM -- Hierarchical Cross Attention Model for Multi-modal Emotion Recognition [41.837538440839815]
  We propose a hierarchical cross-attention model (HCAM) approach to multi-modal emotion recognition. The input to the model consists of two modalities, i) audio data, processed through a learnable wav2vec approach and, ii) text data represented using a bidirectional encoder representations from transformers (BERT) model. In order to incorporate contextual knowledge and the information across the two modalities, the audio and text embeddings are combined using a co-attention layer.
  arXiv  Detail & Related papers  (2023-04-14T03:25:00Z)
• Learning Multimodal Data Augmentation in Feature Space [65.54623807628536]
  LeMDA is an easy-to-use method that automatically learns to jointly augment multimodal data in feature space. We show that LeMDA can profoundly improve the performance of multimodal deep learning architectures.
  arXiv  Detail & Related papers  (2022-12-29T20:39:36Z)
• M2FNet: Multi-modal Fusion Network for Emotion Recognition in Conversation [1.3864478040954673]
  We propose a Multi-modal Fusion Network (M2FNet) that extracts emotion-relevant features from visual, audio, and text modality. It employs a multi-head attention-based fusion mechanism to combine emotion-rich latent representations of the input data. The proposed feature extractor is trained with a novel adaptive margin-based triplet loss function to learn emotion-relevant features from the audio and visual data.
  arXiv  Detail & Related papers  (2022-06-05T14:18:58Z)
• Multimodal Masked Autoencoders Learn Transferable Representations [127.35955819874063]
  We propose a simple and scalable network architecture, the Multimodal Masked Autoencoder (M3AE) M3AE learns a unified encoder for both vision and language data via masked token prediction. We provide an empirical study of M3AE trained on a large-scale image-text dataset, and find that M3AE is able to learn generalizable representations that transfer well to downstream tasks.
  arXiv  Detail & Related papers  (2022-05-27T19:09:42Z)
• MEmoBERT: Pre-training Model with Prompt-based Learning for Multimodal Emotion Recognition [118.73025093045652]
  We propose a pre-training model textbfMEmoBERT for multimodal emotion recognition. Unlike the conventional "pre-train, finetune" paradigm, we propose a prompt-based method that reformulates the downstream emotion classification task as a masked text prediction. Our proposed MEmoBERT significantly enhances emotion recognition performance.
  arXiv  Detail & Related papers  (2021-10-27T09:57:00Z)
• Fusion with Hierarchical Graphs for Mulitmodal Emotion Recognition [7.147235324895931]
  This paper proposes a novel hierarchical graph network (HFGCN) model that learns more informative multimodal representations. Specifically, the proposed model fuses multimodality inputs using a two-stage graph construction approach and encodes the modality dependencies into the conversation representation. Experiments showed the effectiveness of our proposed model for more accurate AER, which yielded state-of-the-art results on two public datasets.
  arXiv  Detail & Related papers  (2021-09-15T08:21:01Z)
• Self-Supervised learning with cross-modal transformers for emotion recognition [20.973999078271483]
  Self-supervised learning has shown improvements on tasks with limited labeled datasets in domains like speech and natural language. In this work, we extend self-supervised training to multi-modal applications.
  arXiv  Detail & Related papers  (2020-11-20T21:38:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.