{"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/lpcnet-improving-neural-speech-synthesis","title":"LPCNet: Improving Neural Speech Synthesis Through Linear Prediction","arxiv_id":"1810.11846","date":"2018-10-28","proceeding":null,"authors":["Jean-Marc Valin","Jan Skoglund"],"abstract":"Neural speech synthesis models have recently demonstrated the ability to\nsynthesize high quality speech for text-to-speech and compression applications.\nThese new models often require powerful GPUs to achieve real-time operation, so\nbeing able to reduce their complexity would open the way for many new\napplications. We propose LPCNet, a WaveRNN variant that combines linear\nprediction with recurrent neural networks to significantly improve the\nefficiency of speech synthesis. We demonstrate that LPCNet can achieve\nsignificantly higher quality than WaveRNN for the same network size and that\nhigh quality LPCNet speech synthesis is achievable with a complexity under 3\nGFLOPS. This makes it easier to deploy neural synthesis applications on\nlower-power devices, such as embedded systems and mobile phones.","url_abs":"http://arxiv.org/abs/1810.11846v2","url_pdf":"http://arxiv.org/pdf/1810.11846v2.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":"lpcnet-improving-neural-speech-synthesis","repo_url":"https://github.com/mozilla/LPCNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"BSD-3-Clause"}},{"paper_slug":"lpcnet-improving-neural-speech-synthesis","repo_url":"https://github.com/2023-MindSpore-1/ms-code-57","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":{"status":"ok"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"},{"method_slug":"wavernn","method_name":"WaveRNN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1810.11846","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}