mlsanityData to 7 Oct 2026

A Preliminary Study on Augmenting Speech Emotion Recognition using a Diffusion Model

arXiv 2305.11413 ↗First posted 19 May 2023cs.SD eess.AScited by 6

On the map: Diffusion models → Audio, speech and music

Abstract (arXiv)

In this paper, we propose to utilise diffusion models for data augmentation in speech emotion recognition (SER). In particular, we present an effective approach to utilise improved denoising diffusion probabilistic models (IDDPM) to generate synthetic emotional data. We condition the IDDPM with the textual embedding from bidirectional encoder representations from transformers (BERT) to generate high-quality synthetic emotional samples in different speakers' voicesfootnotesynthetic samples URL: urlhttps://emulationai.com/research/diffusion-ser.. We implement a series of experiments and show that better quality synthetic data helps improve SER performance. We compare results with generative adversarial networks (GANs) and show that the proposed model generates better-quality synthetic samples that can considerably improve the performance of SER when augmented with synthetic data.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Audio, speech and music, one of 14 directions in Diffusion models. Builds on 22 of its 40 references that are in the map. First posted on arXiv 19 May 2023.

Builds on

22 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis21 Apr

Other references · 21

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  8. 2014Conditional Generative Adversarial Netscited by 2,152
  9. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  10. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  11. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,036
  12. 2018BAGAN: Data Augmentation with Balancing GANcited by 90
9 more
  1. 2023Transformers in Speech Processing: A Surveycited by 38
  2. 2019Direct Modelling of Speech Emotion from Raw Speechcited by 13
  3. 2020Augmenting Generative Adversarial Networks for Speech Emotion Recognitioncited by 11
  4. 2022Multitask Learning from Augmented Auxiliary Data for Improving Speech Emotion Recognitioncited by 11
  5. 2018Transfer Learning for Improving Speech Emotion Classification Accuracycited by 10
  6. 2020Deep Architecture Enhancing Robustness to Noise, Adversarial Attacks, and Cross-corpus Setting for Speech Emotion Recognitioncited by 10
  7. 2018On the Robustness of Speech Emotion Recognition for Human-Robot Interaction with Deep Neural Networkscited by 8
  8. 2023Generative Emotional AI for Speech Emotion Recognition: The Case for Synthetic Emotional Speech Augmentationcited by 8
  9. 2018On Enhancing Speech Emotion Recognition using Generative Adversarial Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 2; 2025: 1; 2026: 1.

6 papers.

  1. 2023Leveraging Speech PTM, Text LLM, and Emotional TTS for Speech Emotion Recognitioncited by 12
  2. 2024Enhancing Low-Resource ASR through Versatile TTS: Bridging the Data Gapcited by 11
  3. 2024The last Dance : Robust backdoor attack via diffusion models and bayesian approachcited by 3
  4. 2023Cross-Language Speech Emotion Recognition Using Multimodal Dual Attention Transformerscited by 1
  5. 2025Improving Speech Emotion Recognition with Mutual Information Regularized Generative Modelcited by 0
  6. 2026Synthetic Speech, Real Signal: Paralinguistic Preservation and Cross-Lingual Augmentation via Voice Cloningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023EMOCONV-DIFF: Diffusion-based Speech Emotion Conversion for Non-parallel and In-the-wild Data
  2. 2023DiffProsody: Diffusion-based Latent Prosody Generation for Expressive Speech Synthesis with Prosody Conditional Adversarial Training
  3. 2024Converting Anyone's Voice: End-to-End Expressive Voice Conversion with a Conditional Diffusion Model
  4. 2024Improvement in Facial Emotion Recognition using Synthetic Data Generated by Diffusion Model
  5. 2023A Survey on Audio Diffusion Models: Text To Speech Synthesis and Enhancement in Generative AI
  6. 2023Diverse and Expressive Speech Prosody Prediction with Denoising Diffusion Probabilistic Model
  7. 2021Noise Estimation for Generative Diffusion Models
  8. 2024Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancement