Neural Speech Synthesis On A Shoestring: Improving The Efficiency Of Lpcnet

Abstract

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.

Stats

• citations5
• S2 citations—
• github stars0
• HF likes0
• heat score5.84
• arxiv keyvalin2022neural

Related papers

• Lpcnet: Improving Neural Speech Synthesis Through Linear Prediction (2018)0.00
• A Real-time Wideband Neural Vocoder At 1.6 Kb/s Using Lpcnet (2019)12.61
• End-to-end Lpcnet: A Neural Vocoder With Fully-differentiable LPC Estimation (2022)7.16
• Controllable Sequence-to-sequence Neural TTS With LPCNET Backend For Real-time Speech Synthesis On CPU (2020)0.00
• High Quality, Lightweight And Adaptable TTS Using Lpcnet (2019)10.97
• Improving Opus Low Bit Rate Quality With Neural Speech Synthesis (2019)10.48
• High Quality Streaming Speech Synthesis With Low, Sentence-length-independent Latency (2021)8.60
• Improving Lpcnet-based Text-to-speech With Linear Prediction-structured Mixture Density Network (2020)5.24