{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-vector-quantized-masked-autoencoder-for","title":"A vector quantized masked autoencoder for speech emotion recognition","arxiv_id":"2304.11117","date":"2023-04-21","proceeding":null,"authors":["Samir Sadok","Simon Leglaive","Renaud Séguier"],"abstract":"Recent years have seen remarkable progress in speech emotion recognition (SER), thanks to advances in deep learning techniques. However, the limited availability of labeled data remains a significant challenge in the field. Self-supervised learning has recently emerged as a promising solution to address this challenge. In this paper, we propose the vector quantized masked autoencoder for speech (VQ-MAE-S), a self-supervised model that is fine-tuned to recognize emotions from speech signals. The VQ-MAE-S model is based on a masked autoencoder (MAE) that operates in the discrete latent space of a vector-quantized variational autoencoder. Experimental results show that the proposed VQ-MAE-S model, pre-trained on the VoxCeleb2 dataset and fine-tuned on emotional speech data, outperforms an MAE working on the raw spectrogram representation and other state-of-the-art methods in SER.","url_abs":"https://arxiv.org/abs/2304.11117v1","url_pdf":"https://arxiv.org/pdf/2304.11117v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-vector-quantized-masked-autoencoder-for","repo_url":"https://github.com/samsad35/VQ-MAE-S-code","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-emotion-recognition","task_name":"Speech Emotion Recognition"}],"methods":[{"method_slug":"mae","method_name":"MAE"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-emotion-recognition-on-emodb-dataset","task":"Speech Emotion Recognition","dataset":"EmoDB Dataset","model":"VQ-MAE-S-12 (Frame) + Query2Emo","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"90.2","F1":"0.891"},"uses_additional_data":false},{"leaderboard":"/sota/speech-emotion-recognition-on-ravdess","task":"Speech Emotion Recognition","dataset":"RAVDESS","model":"VQ-MAE-S-12 (Frame) + Query2Emo","rank_in_archive_order":1,"of":5,"metrics":{"Accuracy":"84.1","F1":"0.844"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}