{"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/multimodal-speech-emotion-recognition-and","title":"Multimodal Speech Emotion Recognition and Ambiguity Resolution","arxiv_id":"1904.06022","date":"2019-04-12","proceeding":null,"authors":["Gaurav Sahu"],"abstract":"Identifying emotion from speech is a non-trivial task pertaining to the\nambiguous definition of emotion itself. In this work, we adopt a\nfeature-engineering based approach to tackle the task of speech emotion\nrecognition. Formalizing our problem as a multi-class classification problem,\nwe compare the performance of two categories of models. For both, we extract\neight hand-crafted features from the audio signal. In the first approach, the\nextracted features are used to train six traditional machine learning\nclassifiers, whereas the second approach is based on deep learning wherein a\nbaseline feed-forward neural network and an LSTM-based classifier are trained\nover the same features. In order to resolve ambiguity in communication, we also\ninclude features from the text domain. We report accuracy, f-score, precision,\nand recall for the different experiment settings we evaluated our models in.\nOverall, we show that lighter machine learning based models trained over a few\nhand-crafted features are able to achieve performance comparable to the current\ndeep learning based state-of-the-art method for emotion recognition.","url_abs":"http://arxiv.org/abs/1904.06022v1","url_pdf":"http://arxiv.org/pdf/1904.06022v1.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":"multimodal-speech-emotion-recognition-and","repo_url":"https://github.com/Cris-Nguyen/Speech-Emotion-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multimodal-speech-emotion-recognition-and","repo_url":"https://github.com/Demfier/multimodal-speech-emotion-recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multimodal-speech-emotion-recognition-and","repo_url":"https://github.com/MagnusXu/Speech-Emotion-Recognition-Capstone-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"multimodal-speech-emotion-recognition-and","repo_url":"https://github.com/SER-2020-Project-ZX/Reference","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"multimodal-speech-emotion-recognition-and","repo_url":"https://github.com/adsieg/Speech","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"emotion-recognition","task_name":"Emotion Recognition"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"multi-class-classification","task_name":"Multi-class Classification"},{"task_slug":"multimodal-emotion-recognition","task_name":"Multimodal Emotion Recognition"},{"task_slug":"speech-emotion-recognition","task_name":"Speech Emotion Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}