{"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/exploring-transfer-learning-for-low-resource","title":"Exploring Transfer Learning for Low Resource Emotional TTS","arxiv_id":"1901.04276","date":"2019-01-14","proceeding":"Advances in Intelligent Systems and Computing 2019 8","authors":["Noé Tits","Kevin El Haddad","Thierry Dutoit"],"abstract":"During the last few years, spoken language technologies have known a big\nimprovement thanks to Deep Learning. However Deep Learning-based algorithms\nrequire amounts of data that are often difficult and costly to gather.\nParticularly, modeling the variability in speech of different speakers,\ndifferent styles or different emotions with few data remains challenging. In\nthis paper, we investigate how to leverage fine-tuning on a pre-trained Deep\nLearning-based TTS model to synthesize speech with a small dataset of another\nspeaker. Then we investigate the possibility to adapt this model to have\nemotional TTS by fine-tuning the neutral TTS model with a small emotional\ndataset.","url_abs":"http://arxiv.org/abs/1901.04276v1","url_pdf":"http://arxiv.org/pdf/1901.04276v1.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":"exploring-transfer-learning-for-low-resource","repo_url":"https://github.com/Emotional-Text-to-Speech/dl-for-emo-tts","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"exploring-transfer-learning-for-low-resource","repo_url":"https://github.com/jessearodriguez/LJ-Audio-dataset-generator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"exploring-transfer-learning-for-low-resource","repo_url":"https://github.com/SeanPLeary/dc_tts-transfer-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"exploring-transfer-learning-for-low-resource","repo_url":"https://github.com/keonlee9420/DailyTalk","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"exploring-transfer-learning-for-low-resource","repo_url":"https://github.com/keonlee9420/Expressive-FastSpeech2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"emotional-speech-synthesis","task_name":"Emotional Speech Synthesis"},{"task_slug":"expressive-speech-synthesis","task_name":"Expressive Speech Synthesis"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1901.04276","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}