2022/02/22 by Jean-Marc Valin, Valin, Jean-Marc, Umut Isik +5
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #Speech and dialogue systems #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2202.11169
openalex publication_date 2022/02/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so. In previous work, we introduced LPCNet, which uses linear prediction to significantly reduce the complexity of neural synthesis. In this work, we further improve the efficiency of LPCNet -- targeting both algorithmic and computational improvements -- to make it usable on a wide variety of devices. We demonstrate an improvement in synthesis quality while operating 2.5x faster. The resulting open-source LPCNet algorithm can perform real-time neural synthesis on most existing phones and is even usable in some embedded devices.