mlsanityData to 7 Oct 2026

Bunched LPCNet2: Efficient Neural Vocoders Covering Devices from Cloud to Edge

arXiv 2203.14416 ↗First posted 27 Mar 2022eess.AS cs.LG cs.SDcited by 0

Not on the map. Why?

Abstract (arXiv)

Text-to-Speech (TTS) services that run on edge devices have many advantages compared to cloud TTS, e.g., latency and privacy issues. However, neural vocoders with a low complexity and small model footprint inevitably generate annoying sounds. This study proposes a Bunched LPCNet2, an improved LPCNet architecture that provides highly efficient performance in high-quality for cloud servers and in a low-complexity for low-resource edge devices. Single logistic distribution achieves computational efficiency, and insightful tricks reduce the model footprint while maintaining speech quality. A DualRate architecture, which generates a lower sampling rate from a prosody model, is also proposed to reduce maintenance costs. The experiments demonstrate that Bunched LPCNet2 generates satisfactory speech quality with a model footprint of 1.1MB while operating faster than real-time on a RPi 3B. Our audio samples are available at https://srtts.github.io/bunchedLPCNet2.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 21 references that are in the map. First posted on arXiv 27 Mar 2022.

Builds on

14 of 21 references.

References · 14

  1. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  2. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  3. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  4. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  5. 2019MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesiscited by 351
  6. 2018WaveGlow: A Flow-based Generative Network for Speech Synthesiscited by 308
  7. 2018Efficient Neural Audio Synthesiscited by 218
  8. 2017Parallel WaveNet: Fast High-Fidelity Speech Synthesiscited by 214
  9. 2018LPCNet: Improving Neural Speech Synthesis Through Linear Predictioncited by 109
  10. 2021High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latencycited by 19
  11. 2020Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systemscited by 16
  12. 2016High-Quality, Low-Delay Music Coding in the Opus Codeccited by 12
2 more
  1. 2020Improving LPCNet-based Text-to-Speech with Linear Prediction-structured Mixture Density Networkcited by 3
  2. 2020FBWave: Efficient and Scalable Neural Vocoders for Streaming Text-To-Speech on the Edgecited by 3

Built on by

Not cited yet.