Data to 13 Oct 2026

LPCNet: Improving Neural Speech Synthesis Through Linear Prediction

arXiv 1810.11846 ↗First posted 28 Oct 2018eess.AS cs.LG cs.SDcited by 110

Not on the map. Why?

Abstract (arXiv)

Neural speech synthesis models have recently demonstrated the ability to synthesize high quality speech for text-to-speech and compression applications. These new models often require powerful GPUs to achieve real-time operation, so being able to reduce their complexity would open the way for many new applications. We propose LPCNet, a WaveRNN variant that combines linear prediction with recurrent neural networks to significantly improve the efficiency of speech synthesis. We demonstrate that LPCNet can achieve significantly higher quality than WaveRNN for the same network size and that high quality LPCNet speech synthesis is achievable with a complexity under 3 GFLOPS. This makes it easier to deploy neural synthesis applications on lower-power devices, such as embedded systems and mobile phones.

Key facts. Cited by 110 papers in the map (data through 13 Oct 2026). First posted on arXiv 28 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 39; 2022: 41; 2023: 11; 2024: 10; 2025: 7; 2026: 2.

110 papers.

Sort:

By area:

2021SoundStream: An End-to-End Neural Audio Codeccited by 762
2022High Fidelity Neural Audio Compressioncited by 680
2021AI Choreographer: Music Conditioned 3D Dance Generation with AIST++cited by 481
2021Speech Resynthesis from Discrete Disentangled Self-Supervised Representationscited by 243
2023NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizerscited by 235
2021A Survey on Neural Speech Synthesiscited by 182
2023Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesiscited by 152
2022COIN++: Neural Compression Across Modalitiescited by 82
2021Neural Analysis and Synthesis: Reconstructing Speech from Self-Supervised Representationscited by 81
2021Half-Truth: A Partially Fake Audio Detection Datasetcited by 44
2022WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iterationcited by 20
2021High Quality Streaming Speech Synthesis with Low, Sentence-Length-Independent Latencycited by 19

38 more

2022SOMOS: The Samsung Open MOS Dataset for the Evaluation of Neural Text-to-Speech Synthesiscited by 18
2022CampNet: Context-Aware Mask Prediction for End-to-End Text-Based Speech Editingcited by 15
2025FlowDec: A flow-based full-band general audio codec with high perceptual qualitycited by 15
2021Context-Aware Prosody Correction for Text-Based Speech Editingcited by 13
2022An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audiocited by 13
2021A Light-weight contextual spelling correction model for customizing transducer-based speech recognition systemscited by 11
2021Restoring degraded speech via a modified diffusion modelcited by 10
2022Fully Automated End-to-End Fake Audio Detectioncited by 10
2021On-device neural speech synthesiscited by 9
2022Audio representations for deep learning in sound synthesis: A reviewcited by 9
2022Lightweight and High-Fidelity End-to-End Text-to-Speech with Multi-Band Generation and Inverse Short-Time Fourier Transformcited by 9
2024RFWave: Multi-band Rectified Flow for Audio Waveform Reconstructioncited by 9
2021Cross-lingual Low Resource Speaker Adaptation Using Phonological Featurescited by 8
2021Prosodic Clustering for Phoneme-level Prosody Control in End-to-End Speech Synthesiscited by 8
2021VocBench: A Neural Vocoder Benchmark for Speech Synthesiscited by 8
2023Speak While You Think: Streaming Speech Synthesis During Text Generationcited by 8
2021Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoderscited by 7
2021PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic componentscited by 7
2021HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Codingcited by 7
2022End-to-End Neural Speech Coding for Real-Time Communicationscited by 7
2022WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Lossescited by 7
2022Latent-Domain Predictive Neural Speech Codingcited by 7
2023Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor and Hierarchical Modeling in Speech Synthesiscited by 7
2024Differentiable All-pole Filters for Time-varying Audio Systemscited by 7
2024RapVerse: Coherent Vocals and Whole-Body Motions Generations from Textcited by 7
2021Review of end-to-end speech synthesis technology based on deep learningcited by 6
2021Scalable and Efficient Neural Speech Coding: A Hybrid Designcited by 5
2021A Streamwise GAN Vocoder for Wideband Speech Coding at Very Low Bit Ratecited by 5
2021Word-Level Style Control for Expressive, Non-attentive Speech Synthesiscited by 5
2022Unified Source-Filter GAN with Harmonic-plus-Noise Source Excitation Generationcited by 5
2022Ultra-Low-Bitrate Speech Coding with Pretrained Transformerscited by 5
2022ParaTTS: Learning Linguistic and Prosodic Cross-sentence Information in Paragraph-based TTScited by 5
2022The Sound of Silence: Efficiency of First Digit Features in Synthetic Audio Detectioncited by 5
2025From Scores to Preferences: Redefining MOS Benchmarking for Speech Quality Reward Modelingcited by 5
2021Learning robust speech representation with an articulatory-regularized variational autoencodercited by 4
2022Singing-Tacotron: Global duration control attention and dynamic filter for End-to-end singing voice synthesiscited by 4
2024Creating an African American-Sounding TTS: Guidelines, Technical Challenges,and Surprising Evaluationscited by 4
2024Decoupled Weight Decay for Any p Normcited by 4

50 most cited of 110 All 110 (JSON)