{"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/attention-augmented-end-to-end-multi-task","title":"Attention-Augmented End-to-End Multi-Task Learning for Emotion Prediction from Speech","arxiv_id":"1903.12424","date":"2019-03-29","proceeding":null,"authors":["Zixing Zhang","Bingwen Wu","Bjoern Schuller"],"abstract":"Despite the increasing research interest in end-to-end learning systems for\nspeech emotion recognition, conventional systems either suffer from the\noverfitting due in part to the limited training data, or do not explicitly\nconsider the different contributions of automatically learnt representations\nfor a specific task. In this contribution, we propose a novel end-to-end\nframework which is enhanced by learning other auxiliary tasks and an attention\nmechanism. That is, we jointly train an end-to-end network with several\ndifferent but related emotion prediction tasks, i.e., arousal, valence, and\ndominance predictions, to extract more robust representations shared among\nvarious tasks than traditional systems with the hope that it is able to relieve\nthe overfitting problem. Meanwhile, an attention layer is implemented on top of\nthe layers for each task, with the aim to capture the contribution distribution\nof different segment parts for each individual task. To evaluate the\neffectiveness of the proposed system, we conducted a set of experiments on the\nwidely used database IEMOCAP. The empirical results show that the proposed\nsystems significantly outperform corresponding baseline systems.","url_abs":"http://arxiv.org/abs/1903.12424v1","url_pdf":"http://arxiv.org/pdf/1903.12424v1.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":"attention-augmented-end-to-end-multi-task","repo_url":"https://github.com/raulsteleac/Speech_Emotion_Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"speech-emotion-recognition","task_name":"Speech Emotion Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1903.12424","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}